You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/04/01 03:34:50 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@98007f90d8d60a77e997dc79c2cfc5d7e9c85ebb)
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 91c7f90be1 deploying docs (apache/tvm@98007f90d8d60a77e997dc79c2cfc5d7e9c85ebb)
91c7f90be1 is described below
commit 91c7f90be1f20dda695ec46cd358971b312b0196
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sat Apr 1 03:34:43 2023 +0000
deploying docs (apache/tvm@98007f90d8d60a77e997dc79c2cfc5d7e9c85ebb)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 341097 -> 344888 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24317 -> 24077 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 7 +-
.../deploy_model_on_adreno_tvmc.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 22 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 479 +++++++---
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 32 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 4 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 993 +--------------------
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 14 +-
.../work_with_relay/sg_execution_times.rst.txt | 10 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 16 +-
docs/how_to/compile_models/from_pytorch.html | 11 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 3 +-
.../deploy_models/deploy_model_on_adreno_tvmc.html | 15 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 61 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 40 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 479 +++++++---
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 32 +-
.../tune_with_autotvm/sg_execution_times.html | 4 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 993 +--------------------
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 6 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 14 +-
.../how_to/work_with_relay/sg_execution_times.html | 10 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
docs/reference/api/typedoc/classes/instance.html | 58 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
.../api/typedoc/classes/runtimecontext.html | 22 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
docs/reference/api/typedoc/classes/tvmarray.html | 16 +-
docs/reference/api/typedoc/classes/tvmobject.html | 12 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 124 +--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 10 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 276 +++---
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 18 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
129 files changed, 1719 insertions(+), 3029 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 60e9d514ac..03eff51625 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 537d31c680..ce827177eb 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 ddb5aa2d38..5e19a98d69 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.354 seconds)
+ **Total running time of the script:** ( 1 minutes 21.309 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index deb202b0d4..fd9f1b24f6 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipc6b04538-23f3-4d1b-9feb-d5fcfb06ed08 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip4b04227a-1808-458c-bcfc-7a49db732363 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 18886269f0..a06160b578 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 55.7MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 57.8MB/s]
48%|####7 | 19.9M/41.5M [00:00<00:00, 45.1MB/s]
59%|#####8 | 24.4M/41.5M [00:00<00:00, 35.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 36.4MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 39.2MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 40.8MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 63.4MB/s]
30%|##9 | 12.4M/41.5M [00:00<00:00, 59.4MB/s]
43%|####3 | 18.0M/41.5M [00:00<00:00, 42.4MB/s]
54%|#####4 | 22.5M/41.5M [00:00<00:00, 41.4MB/s]
64%|######4 | 26.6M/41.5M [00:00<00:00, 34.0MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 29.1MB/s]
89%|########8 | 36.8M/41.5M [00:01<00:00, 33.5MB/s]
97%|#########7| 40.4M/41.5M [00:01<00:00, 27.4MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 34.3MB/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 4b6f8bbf7c..e9c9c4e28e 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 78.2MB/s]
40%|#### | 18.1M/44.7M [00:00<00:00, 60.2MB/s]
54%|#####4 | 24.1M/44.7M [00:00<00:00, 45.3MB/s]
68%|######7 | 30.3M/44.7M [00:00<00:00, 41.8MB/s]
85%|########4 | 37.8M/44.7M [00:00<00:00, 50.7MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 54.3MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
32%|###2 | 14.3M/44.7M [00:00<00:00, 103MB/s]
54%|#####4 | 24.1M/44.7M [00:00<00:00, 84.8MB/s]
72%|#######2 | 32.2M/44.7M [00:00<00:00, 64.4MB/s]
89%|########9 | 39.8M/44.7M [00:00<00:00, 68.6MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 69.7MB/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 397c5306d6..bad9ce2b54 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -430,7 +430,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.713 seconds)
+ **Total running time of the script:** ( 1 minutes 31.163 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 7baf711c30..f3454ca6c2 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**06:59.758** total execution time for **how_to_compile_models** files:
+**06:51.194** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:32.713 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:31.163 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:22.354 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:21.309 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:58.894 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:57.132 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.824 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.155 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.975 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:31.883 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.674 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.913 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:29.050 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:28.917 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.926 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.060 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:24.617 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:23.946 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.731 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.717 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
index 107855a72c..3ae329bc88 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -637,13 +637,18 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2538.6539 2538.4716 2541.9388 2536.9734 1.4015
+ 3334.5961 3332.9302 3346.3906 3331.5372 4.1951
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 4.080 seconds)
+
+
.. _sphx_glr_download_how_to_deploy_models_deploy_model_on_adreno.py:
.. only:: html
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
index 8d341897cb..2cee393b25 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
@@ -127,7 +127,7 @@ Make a Keras Resnet50 Model
.. code-block:: none
Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
-
8192/102967424 [..............................] - ETA: 0s
5701632/102967424 [>.............................] - ETA: 0s
8380416/102967424 [=>............................] - ETA: 1s
16769024/102967424 [===>..........................] - ETA: 1s
23412736/102967424 [=====>........................] - ETA: 1s
25157632/102967424 [======>.......................] - ETA: 1s
31432704/102967424 [========>.....................] - ETA: 1s
33546240/102967424 [========>.....................] - ETA: 1s
41934848/102967424 [===========>..................] - ETA: 1s
48578560/102967424 [=============>................] - ETA: 0s
50323456/102967424 [=============>................] - ETA: 0s
50462720/102967424 [=============>................] - ETA: 1s
58712064/102967424 [================>.............] - ETA: 0s
65355776/102967424 [==================>...........] - ETA: 0s
67100672/102967424 [==================>...........] - ETA: 0s
69296128/102967424 [===================>..........] -
ETA: 0s
72540160/102967424 [====================>.........] - ETA: 0s
75489280/102967424 [====================>.........] - ETA: 0s
82124800/102967424 [======================>.......] - ETA: 0s
83877888/102967424 [=======================>......] - ETA: 0s
90521600/102967424 [=========================>....] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
98910208/102967424 [===========================>..] - ETA: 0s
102850560/102967424
[============================>.] - ETA: 0s
102967424/102967424 [==============================] - 2s 0us/step
+
8192/102967424 [..............................] - ETA: 0s
8380416/102967424 [=>............................] - ETA: 1s
15024128/102967424 [===>..........................] - ETA: 1s
16769024/102967424 [===>..........................] - ETA: 1s
25157632/102967424 [======>.......................] - ETA: 1s
33546240/102967424 [========>.....................] - ETA: 0s
40189952/102967424 [==========>...................] - ETA: 0s
41934848/102967424 [===========>..................] - ETA: 1s
50323456/102967424 [=============>................] - ETA: 0s
52518912/102967424 [==============>...............] - ETA: 0s
55746560/102967424 [===============>..............] - ETA: 0s
58712064/102967424 [================>.............] - ETA: 0s
67100672/102967424 [==================>...........] - ETA: 0s
69296128/102967424 [===================>..........] - ETA: 0s
72540160/102967424 [====================>.........] - ETA: 0s
75489280/102967424 [====================>.........] -
ETA: 0s
83877888/102967424 [=======================>......] - ETA: 0s
90521600/102967424 [=========================>....] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
98910208/102967424 [===========================>..] - ETA: 0s
100646912/102967424 [============================>.] - ETA: 0s
101031936/102967424 [============================>.] - ETA: 0s
102850560/102967424 [============================>.] - ETA: 0s
102967424/102967424
[==============================] - 2s 0us/step
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 72aeeea2c8..0435081034 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3938 16.3993 16.8581 15.9140 0.4216
+ 15.8672 15.7627 16.7829 15.4190 0.3903
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 ab714fc799..4e06021198 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:07, 22.9MB/s]
7%|6 | 11.5M/170M [00:00<00:04, 33.4MB/s]
9%|9 | 16.0M/170M [00:00<00:05, 29.3MB/s]
11%|#1 | 19.2M/170M [00:00<00:05, 29.6MB/s]
14%|#4 | 24.0M/170M [00:00<00:04, 35.0MB/s]
19%|#8 | 32.0M/170M [00:00<00:03, 38.9MB/s]
24%|##3 | 40.0M/170M [00:01<00:02, 47.3MB/s]
28%|##8 | 48.0M/170M [00:01<00:02, 54.0MB/s]
33%|###2 | 56.0M/170M [00:01<00:01, 61.4MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 57.6MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 59.8MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 57.1MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 53.2MB/s]
56%|#####5 | 94.3M/170M [00:02<00:02, 38.4MB/s]
58%|#####8 | 98.6M/170M [00:02<00:01, 37.8MB/s]
61%|######1 | 104M/170M [00:02<00:01, 34.6MB/s]
66%|######5 | 112M/170M [00:02<00:01, 41.4MB/s
]
71%|####### | 120M/170M [00:02<00:01, 47.5MB/s]
75%|#######5 | 128M/170M [00:03<00:00, 47.1MB/s]
79%|#######9 | 134M/170M [00:03<00:00, 49.0MB/s]
82%|########1 | 139M/170M [00:03<00:00, 48.1MB/s]
85%|########4 | 144M/170M [00:03<00:00, 46.5MB/s]
88%|########8 | 150M/170M [00:03<00:00, 48.5MB/s]
91%|#########1| 155M/170M [00:03<00:00, 42.0MB/s]
94%|#########4| 160M/170M [00:03<00:00, 40.9MB/s]
99%|#########8| 168M/170M [00:03<00:00, 47.2MB/s]
100%|##########| 170M/170M [00:03<00:00, 45.0MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:04, 39.8MB/s]
6%|5 | 10.1M/170M [00:00<00:05, 32.8MB/s]
8%|8 | 14.3M/170M [00:00<00:05, 27.7MB/s]
10%|9 | 17.0M/170M [00:00<00:06, 26.0MB/s]
13%|#3 | 22.3M/170M [00:00<00:04, 32.7MB/s]
17%|#7 | 29.2M/170M [00:00<00:03, 43.1MB/s]
20%|#9 | 33.6M/170M [00:01<00:05, 28.4MB/s]
24%|##3 | 40.0M/170M [00:01<00:04, 32.2MB/s]
27%|##7 | 46.3M/170M [00:01<00:03, 32.6MB/s]
29%|##9 | 49.8M/170M [00:01<00:04, 28.3MB/s]
33%|###2 | 56.0M/170M [00:01<00:03, 31.7MB/s]
37%|###6 | 62.3M/170M [00:01<00:03, 37.0MB/s]
39%|###8 | 66.2M/170M [00:02<00:03, 31.4MB/s]
42%|####2 | 72.0M/170M [00:02<00:02, 35.0MB/s]
46%|####6 | 78.3M/170M [00:02<00:02, 35.0MB/s]
48%|####8 | 81.8M/170M [00:02<00:03, 29.7MB/s]
52%|#####1 | 88.0M/170M [00:02<00:02, 30.0MB/
s]
57%|#####6 | 96.0M/170M [00:03<00:02, 37.2MB/s]
60%|###### | 102M/170M [00:03<00:01, 43.1MB/s]
63%|######2 | 107M/170M [00:03<00:01, 43.9MB/s]
66%|######5 | 112M/170M [00:03<00:01, 41.0MB/s]
71%|####### | 120M/170M [00:03<00:01, 40.9MB/s]
75%|#######5 | 128M/170M [00:03<00:01, 42.5MB/s]
79%|#######9 | 134M/170M [00:04<00:00, 38.0MB/s]
81%|########1 | 138M/170M [00:04<00:00, 34.8MB/s]
85%|########4 | 144M/170M [00:04<00:00, 31.4MB/s]
88%|########8 | 150M/170M [00:04<00:00, 34.1MB/s]
90%|######### | 154M/170M [00:04<00:00, 33.7MB/s]
93%|#########3| 158M/170M [00:04<00:00, 35.4MB/s]
95%|#########5| 162M/170M [00:04<00:00, 32.9MB/s]
98%|#########7| 166M/170M [00:05<00:00, 34.1MB/s]
100%|##########| 170M/170M [00:05<00:00, 34.6MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 40.580 seconds)
+ **Total running time of the script:** ( 3 minutes 31.281 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 671522c9a2..f72febca60 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 70.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 88.3MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
47%|####6 | 6.30M/13.6M [00:00<00:00, 55.6MB/s]
86%|########5 | 11.6M/13.6M [00:00<00:00, 49.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 43.7MB/s]
@@ -409,7 +409,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4813 90.4530 91.7494 90.0229 0.3207
+ 90.0886 90.0133 91.4481 89.8131 0.2543
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 17.322 seconds)
+ **Total running time of the script:** ( 1 minutes 15.570 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 b746bbf5d5..724ab320dc 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -423,7 +423,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.3480 120.0775 126.6966 119.3052 1.1110
+ 117.5498 117.1134 122.2979 115.9022 1.3083
@@ -460,7 +460,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 35.047 seconds)
+ **Total running time of the script:** ( 2 minutes 28.407 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 88bfd5221e..3a422a9311 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 42.444 seconds)
+ **Total running time of the script:** ( 1 minutes 51.012 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 675848a08b..e341c9836a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
1%| | 1202/132723 [00:00<00:10, 11977.55KB/s]
3%|2 | 3778/132723 [00:00<00:06, 20055.49KB/s]
7%|7 | 9298/132723 [00:00<00:03, 36078.60KB/s]
13%|#2 | 16863/132723 [00:00<00:02, 51685.42KB/s]
18%|#8 | 24389/132723 [00:00<00:01, 60177.91KB/s]
25%|##4 | 32847/132723 [00:00<00:01, 68468.77KB/s]
31%|###1 | 41570/132723 [00:00<00:01, 74593.79KB/s]
38%|###7 | 50375/132723 [00:00<00:01, 78874.33KB/s]
44%|####4 | 59024/132723 [00:00<00:00, 81252.89KB/s]
51%|#####1 | 67871/132723 [00:01<00:00, 83477.87KB/s]
58%|#####7 | 76593/132723 [00:01<00:00, 84619.21KB/s]
64%|######4 | 85379/132723 [00:01<00:00, 85603.01KB/s]
71%|####### | 94101/132723 [00:01<00:00, 86088.35KB/s]
77%|#######7 | 102837/132723 [00:01<00:00, 86468.14KB/s]
84%|########4 | 111542/132723 [00:01<00:00, 86641.54KB/s]
91%|######### |
120393/132723 [00:01<00:00, 87199.92KB/s]
97%|#########7| 129114/132723 [00:01<00:00, 87189.04KB/s]
100%|##########| 132723/132723 [00:01<00:00, 76108.50KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
1%|1 | 1361/132723 [00:00<00:09, 13564.51KB/s]
3%|3 | 4337/132723 [00:00<00:05, 23022.43KB/s]
8%|8 | 10993/132723 [00:00<00:02, 42860.31KB/s]
12%|#2 | 16506/132723 [00:00<00:02, 46920.89KB/s]
18%|#8 | 24365/132723 [00:00<00:01, 58209.45KB/s]
23%|##3 | 30828/132723 [00:00<00:01, 60374.52KB/s]
28%|##7 | 36873/132723 [00:00<00:01, 50249.48KB/s]
32%|###1 | 42161/132723 [00:00<00:01, 50777.97KB/s]
37%|###6 | 48828/132723 [00:00<00:01, 55290.76KB/s]
41%|####1 | 54531/132723 [00:01<00:01, 55518.88KB/s]
48%|####7 | 63090/132723 [00:01<00:01, 64265.90KB/s]
52%|#####2 | 69646/132723 [00:01<00:01, 51349.87KB/s]
59%|#####8 | 77840/132723 [00:01<00:00, 58992.34KB/s]
64%|######4 | 84961/132723 [00:01<00:00, 62204.26KB/s]
71%|####### | 93677/132723 [00:01<00:00, 69019.86KB/s]
76%|#######6 |
100928/132723 [00:01<00:00, 66187.94KB/s]
83%|########2 | 109761/132723 [00:01<00:00, 72272.30KB/s]
88%|########8 | 117228/132723 [00:02<00:00, 64378.96KB/s]
95%|#########4| 126085/132723 [00:02<00:00, 70721.89KB/s]
100%|##########| 132723/132723 [00:02<00:00, 60273.32KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 53.517 seconds)
+ **Total running time of the script:** ( 3 minutes 47.991 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 b74746cc0b..005fc1dca0 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
Computation times
=================
-**16:38.325** total execution time for **how_to_deploy_models** files:
+**16:27.313** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:53.517 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:47.991 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:40.580 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:31.281 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:35.047 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.407 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.444 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:51.012 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:17.322 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:15.570 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.238 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:04.080 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:52.695 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:51.543 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:43.600 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:42.127 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:29.213 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.864 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:28.661 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.433 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index e58b66b1bf..147477065b 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -463,7 +463,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipea86d14c-92aa-44ff-b9e9-88d6eae93f8e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipa2ab9eb9-ad64-4742-95fb-8a6404a16976 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 c6f015c527..52cf5b312b 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
=================
-**00:55.266** total execution time for **how_to_extend_tvm** files:
+**00:53.389** 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``) | 00:51.370 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:49.685 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.787 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.655 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.103 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.041 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 193d692b12..8ce5101d4b 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 22811us [22811us] (48.95%; 48.95%)
- FoldScaleAxis: 23789us [7us] (51.05%; 51.05%)
- FoldConstant: 23781us [1740us] (51.03%; 99.97%)
- InferType: 22041us [22041us] (47.30%; 92.68%)
+ InferType: 22481us [22481us] (48.76%; 48.76%)
+ FoldScaleAxis: 23626us [6us] (51.24%; 51.24%)
+ FoldConstant: 23619us [1689us] (51.23%; 99.97%)
+ InferType: 21930us [21930us] (47.56%; 92.85%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 24287us [24287us] (49.83%; 49.83%)
- FoldScaleAxis: 24455us [7us] (50.17%; 50.17%)
- FoldConstant: 24448us [2124us] (50.16%; 99.97%)
- InferType: 22324us [22324us] (45.80%; 91.31%)
+ InferType: 21839us [21839us] (47.73%; 47.73%)
+ FoldScaleAxis: 23918us [5us] (52.27%; 52.27%)
+ FoldConstant: 23914us [1681us] (52.26%; 99.98%)
+ InferType: 22233us [22233us] (48.59%; 92.97%)
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 a0149525ee..d80fe93508 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 38.695518 ms
+ Convolution: 53.501697 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 91caa39025..19a6cb74d4 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -598,7 +598,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.220621 ms
+ conv2d with tensor core: 12.235994 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 5e3f867f95..d8ecb92ccf 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018600
- Baseline: 3.413767
+ Numpy running time: 0.017715
+ Baseline: 3.290472
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.306455
+ Opt1: 0.308936
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.337015
+ Opt2: 0.335496
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117997
+ Opt3: 0.113693
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110633
+ Opt4: 0.109619
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111351
+ Opt5: 0.111150
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147289
+ Opt6: 0.146615
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 e795c42573..8c864764d8 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.535** total execution time for **how_to_optimize_operators** files:
+**00:35.126** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.574 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.049 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.893 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.852 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.068 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.226 | 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 d173d35040..4031ad74b2 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**10:23.015** total execution time for **how_to_tune_with_autoscheduler** files:
+**10:04.077** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:25.382 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:12.159 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:44.112 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:41.520 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:11.997 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:10.557 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:33.415 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:32.503 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.366 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:13.961 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.743 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.377 | 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 85b40a3ba8..41a070b61b 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
@@ -243,74 +243,199 @@ cooperative fetching, unrolling and operator fusion.
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- blockIdx_x = T.launch_thread("blockIdx.x", 32)
- conv2d_nchw = T.allocate([8], "float32", "local")
- pad_temp_shared = T.allocate([784], "float32", "shared")
- kernel_shared = T.allocate([256], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 98)
- conv2d_nchw_1 = T.Buffer((16,), data=conv2d_nchw, scope="local", align=16)
+ blockIdx_x = T.launch_thread("blockIdx.x", 16)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([2016], "float32", "shared")
+ kernel_shared = T.allocate([3072], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 112)
+ conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
conv2d_nchw_1[7] = T.float32(0)
- for rc_outer_outer, ry_outer_outer, rx_outer_outer in T.grid(32, 3, 3):
- cse_var_2: T.int32 = rc_outer_outer * 144
- cse_var_1: T.int32 = ry_outer_outer * 3
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
+ conv2d_nchw_1[13] = T.float32(0)
+ for rc_outer_outer, rx_outer_outer in T.grid(16, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 1568
+ cse_var_1: T.int32 = rc_outer_outer * 288
+ pad_temp_shared_1 = T.Buffer((2016,), data=pad_temp_shared, scope="shared")
+ with T.launch_thread("threadIdx.x", 112) as threadIdx_x_1:
+ data_1 = T.Buffer((25088,), data=data.data)
+ pad_temp_shared_1[threadIdx_x_1 * 18] = T.if_then_else(7 < threadIdx_x_1 * 18 % 63 and threadIdx_x_1 * 18 % 63 < 56 and 1 <= rx_outer_outer + threadIdx_x_1 * 4 % 7 and rx_outer_outer + threadIdx_x_1 * 4 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + threadIdx_x_1 * 18 % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 1] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 1) % 63 and (threadIdx_x_1 * 18 + 1) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 1) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 2] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 2) % 63 and (threadIdx_x_1 * 18 + 2) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 2) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 3] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 3) % 63 and (threadIdx_x_1 * 18 + 3) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 3) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 4] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 4) % 63 and (threadIdx_x_1 * 18 + 4) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 4) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 4) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 4) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 5] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 5) % 63 and (threadIdx_x_1 * 18 + 5) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 5) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 5) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 5) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 6] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 6) % 63 and (threadIdx_x_1 * 18 + 6) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 6) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 6) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 6) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 7] = T.if_then_else(1 <= (threadIdx_x_1 * 18 // 7 + 1) % 9 and (threadIdx_x_1 * 18 + 7) % 63 < 56 and 1 <= rx_outer_outer + threadIdx_x_1 * 4 % 7 and rx_outer_outer + threadIdx_x_1 * 4 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 7) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 8] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 8) % 63 and (threadIdx_x_1 * 18 + 8) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 8) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 9] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 9) % 63 and (threadIdx_x_1 * 18 + 9) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 9) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 10] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 10) % 63 and (threadIdx_x_1 * 18 + 10) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 10) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 11] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 11) % 63 and (threadIdx_x_1 * 18 + 11) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 4) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 4) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 11) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 12] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 12) % 63 and (threadIdx_x_1 * 18 + 12) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 5) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 5) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 12) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 13] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 13) % 63 and (threadIdx_x_1 * 18 + 13) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 6) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 6) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 13) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 14] = T.if_then_else(1 <= (threadIdx_x_1 * 18 // 7 + 2) % 9 and (threadIdx_x_1 * 18 + 14) % 63 < 56 and 1 <= rx_outer_outer + threadIdx_x_1 * 4 % 7 and rx_outer_outer + threadIdx_x_1 * 4 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 14) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 15] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 15) % 63 and (threadIdx_x_1 * 18 + 15) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 15) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 16] = T.if_then_else(7 <= (threadIdx_x_1 * 18 + 16) % 63 and (threadIdx_x_1 * 18 + 16) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 16) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 17] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 17) % 63 and (threadIdx_x_1 * 18 + 17) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 17) % 63 - 8], T.float32(0))
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((784,), data=pad_temp_shared, scope="shared")
- data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 90], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 188], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 286], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 384], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 482], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 580], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 678], T.float32(0))
- threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((256,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((3072,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 16 * 4608 + cse_var_2 + threadIdx_x_2 % 16 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 16 * 4608 + cse_var_2 + (threadIdx_x_2 + 2) % 16 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 98):
- if T.likely(threadIdx_x_2 < 60):
- kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 16 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 16 * 9 + cse_var_1 + rx_outer_outer]
- for rc_outer_inner in range(8):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 128]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 16]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 144]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 1]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 129]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 17]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 145]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 32]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 160]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 48]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 176]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 33]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 161]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 49]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 177]
- for i1_inner in range(4):
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 112) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 112) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 224) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 224) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 336) // 96 * 96 + (threadIdx_x_1 // 3 + 16) % 32 * 3 + threadIdx_x_1 % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 336) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 // 3 + 16) % 32 * 9 + threadIdx_x_1 % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 448) // 96 * 96 + (threadIdx_x_1 + 64) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 448) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 64) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 560) // 96 * 96 + (threadIdx_x_1 + 80) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 560) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 80) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1 + 672] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer + 32256]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 784) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 784) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 896) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 896) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1008) // 96 * 96 + (threadIdx_x_1 // 3 + 16) % 32 * 3 + threadIdx_x_1 % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1008) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 // 3 + 16) % 32 * 9 + threadIdx_x_1 % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1120) // 96 * 96 + (threadIdx_x_1 + 64) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1120) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 64) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1232) // 96 * 96 + (threadIdx_x_1 + 80) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1232) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 80) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1 + 1344] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer + 64512]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1456) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1456) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1568) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1568) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1680) // 96 * 96 + (threadIdx_x_1 // 3 + 16) % 32 * 3 + threadIdx_x_1 % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1680) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 // 3 + 16) % 32 * 9 + threadIdx_x_1 % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1792) // 96 * 96 + (threadIdx_x_1 + 64) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1792) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 64) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1904) // 96 * 96 + (threadIdx_x_1 + 80) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1904) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 80) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1 + 2016] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer + 96768]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2128) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2128) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2240) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2240) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2352) // 96 * 96 + (threadIdx_x_1 // 3 + 16) % 32 * 3 + threadIdx_x_1 % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2352) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 // 3 + 16) % 32 * 9 + threadIdx_x_1 % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2464) // 96 * 96 + (threadIdx_x_1 + 64) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2464) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 64) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2576) // 96 * 96 + (threadIdx_x_1 + 80) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2576) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 80) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1 + 2688] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer + 129024]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2800) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2800) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2912) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2912) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ if T.likely(threadIdx_x_1 < 48):
+ kernel_shared_1[(threadIdx_x_1 + 3024) // 96 * 96 + threadIdx_x_1 + 48] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 3024) // 96 * 4608 + cse_var_1 + threadIdx_x_1 * 3 + rx_outer_outer + 144]
+ for rc_outer_inner in range(16):
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ for i1_inner, i2_inner in T.grid(2, 7):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 196 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 4 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 196 + i1_inner * 49 + threadIdx_x % 49 + 392] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 4 + i1_inner + 8], T.float32(0))
+ compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i1_inner * 7 + i2_inner] + bias_1[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
@@ -360,7 +485,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.259 ms
+ Execution time of this operator: 0.271 ms
@@ -408,33 +533,33 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
- conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -457,14 +582,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=18)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -482,60 +607,168 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[784];
- __shared__ float kernel_shared[256];
+ extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 90)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 188)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 286)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 482)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 580)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 2) & 15) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 60) {
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 4) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 4) & 15) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 128)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 144)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 145)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 160)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 176)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 161)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 49)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 177)]));
- }
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 18)] = (((((7 < ((((int)threadIdx.x) * 18) % 63)) && (((((int)threadIdx.x) * 18) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + ((((int)threadIdx.x) * 18) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 1)] = (((((7 < (((((int)threadIdx.x) * 18) + 1) % 63)) && ((((((int)threadIdx.x) * 18) + 1) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 1) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 2)] = (((((7 < (((((int)threadIdx.x) * 18) + 2) % 63)) && ((((((int)threadIdx.x) * 18) + 2) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 2) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 3)] = (((((7 < (((((int)threadIdx.x) * 18) + 3) % 63)) && ((((((int)threadIdx.x) * 18) + 3) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 3) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 4)] = (((((7 < (((((int)threadIdx.x) * 18) + 4) % 63)) && ((((((int)threadIdx.x) * 18) + 4) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 4) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 5)] = (((((7 < (((((int)threadIdx.x) * 18) + 5) % 63)) && ((((((int)threadIdx.x) * 18) + 5) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 5) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 5) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 5) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 6)] = (((((7 < (((((int)threadIdx.x) * 18) + 6) % 63)) && ((((((int)threadIdx.x) * 18) + 6) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 6) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 6) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 6) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 7)] = (((((1 <= ((((((int)threadIdx.x) * 18) / 7) + 1) % 9)) && ((((((int)threadIdx.x) * 18) + 7) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 7) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 8)] = (((((7 < (((((int)threadIdx.x) * 18) + 8) % 63)) && ((((((int)threadIdx.x) * 18) + 8) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 8) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 9)] = (((((7 < (((((int)threadIdx.x) * 18) + 9) % 63)) && ((((((int)threadIdx.x) * 18) + 9) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 9) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 10)] = (((((7 < (((((int)threadIdx.x) * 18) + 10) % 63)) && ((((((int)threadIdx.x) * 18) + 10) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 10) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 11)] = (((((7 < (((((int)threadIdx.x) * 18) + 11) % 63)) && ((((((int)threadIdx.x) * 18) + 11) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 11) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 12)] = (((((7 < (((((int)threadIdx.x) * 18) + 12) % 63)) && ((((((int)threadIdx.x) * 18) + 12) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 5) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 5) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 12) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 13)] = (((((7 < (((((int)threadIdx.x) * 18) + 13) % 63)) && ((((((int)threadIdx.x) * 18) + 13) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 6) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 6) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 13) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 14)] = (((((1 <= ((((((int)threadIdx.x) * 18) / 7) + 2) % 9)) && ((((((int)threadIdx.x) * 18) + 14) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 14) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 15)] = (((((7 < (((((int)threadIdx.x) * 18) + 15) % 63)) && ((((((int)threadIdx.x) * 18) + 15) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 15) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 16)] = (((((7 <= (((((int)threadIdx.x) * 18) + 16) % 63)) && ((((((int)threadIdx.x) * 18) + 16) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 16) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 17)] = (((((7 < (((((int)threadIdx.x) * 18) + 17) % 63)) && ((((((int)threadIdx.x) * 18) + 17) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 17) % 63)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 112) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 224) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 336) / 96) * 96) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 96) * 96) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 560) / 96) * 96) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((((((int)threadIdx.x) + 784) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 896) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1008) / 96) * 96) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1120) / 96) * 96) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1232) / 96) * 96) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 64512)];
+ kernel_shared[(((((((int)threadIdx.x) + 1456) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1568) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1680) / 96) * 96) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1792) / 96) * 96) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1904) / 96) * 96) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 96768)];
+ kernel_shared[(((((((int)threadIdx.x) + 2128) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2240) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2352) / 96) * 96) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2464) / 96) * 96) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2576) / 96) * 96) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 129024)];
+ kernel_shared[(((((((int)threadIdx.x) + 2800) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2912) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 48) {
+ kernel_shared[(((((((int)threadIdx.x) + 3024) / 96) * 96) + ((int)threadIdx.x)) + 48)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 144)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 126) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 126) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
}
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 8)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -595,7 +828,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 25.382 seconds)
+ **Total running time of the script:** ( 6 minutes 12.159 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 ee7bafa94b..b35172a59f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.1330 8.1306 8.1398 8.1287 0.0049
+ 8.0998 8.0989 8.1043 8.0962 0.0034
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.997 seconds)
+ **Total running time of the script:** ( 1 minutes 10.557 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 2ee05d4566..aca19dc03a 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 760.4988 760.7738 763.0901 757.6325 2.2365
+ 742.0950 742.4272 742.7905 741.0674 0.7416
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 44.112 seconds)
+ **Total running time of the script:** ( 1 minutes 41.520 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 77accef227..4741cd2869 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -389,26 +389,26 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.Buffer((1024,), data=compute_1)
- for i_inner_init, j_init in T.grid(64, 16):
- compute_2[i_inner_init * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 32}), 64, 16):
- cse_var_1 = T.int32()
- placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_2: T.int32 = i0_outer_i1_outer_fused % 32
- if T.likely(elem_idx < placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]):
+ for i0_outer_i1_outer_fused in T.parallel(1024):
+ compute_1 = T.allocate([64], "float32", "global")
+ compute_2 = T.Buffer((64,), data=compute_1)
+ for nb_j_inner in range(2):
+ for i_inner_init, j_init in T.grid(2, 16):
+ compute_2[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 2, 16):
+ cse_var_1 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- cse_var_3: T.int32 = i_inner * 16 + j
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_2] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_2] + elem_idx]], T.float32(0))
- for i0_inner in range(64):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 32 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 512 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner in range(2):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 1024 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_4:cse_var_4 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_4:cse_var_4 + 16], T.Broadcast(T.float32(0), 16))
+ compute_3[cse_var_4:cse_var_4 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
@@ -458,7 +458,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.797 ms
+ Execution time of this operator: 1.879 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 551d715e22..b770567cd3 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:56.140** total execution time for **how_to_tune_with_autotvm** files:
+**00:56.794** 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``) | 00:56.105 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:56.760 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 a0e209e2d7..e56b09e157 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
@@ -390,7 +390,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4038283
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2316543
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -513,9 +513,28 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6833871
- No: 3 GFLOPS: 12.77/12.77 result: MeasureResult(costs=(0.0181309445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6604640483856201, timestamp=1680264160.6413214) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6797780
- No: 4 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
+ 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, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1772544
+ No: 3 GFLOPS: 242.17/242.17 result: MeasureResult(costs=(0.0009559260745341616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4570045471191406, timestamp=1680316947.9738998) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7012841
+ No: 4 GFLOPS: 160.47/242.17 result: MeasureResult(costs=(0.0014426688571428572,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0958614349365234, timestamp=1680316950.4147267) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8870647
+ No: 5 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3807167
+ No: 6 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -637,8 +656,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4629381
- No: 5 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2560072
+ No: 7 GFLOPS: 143.47/242.17 result: MeasureResult(costs=(0.0016135418309859155,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0929834842681885, timestamp=1680316962.9643157) [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 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', 512), ('unroll_explicit', 1)],None,7174023
+ No: 8 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -760,929 +780,11 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5062473
- No: 6 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 399, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 179, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007fba0c91bfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:187
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
- Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,237442
- No: 7 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6735081
- No: 8 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9024820
- No: 9 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10342907
- No: 10 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3760478
- No: 11 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10288904
- No: 12 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 399, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 179, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007f89cd349fa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:187
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
- Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2225951
- No: 13 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2972689
+ No: 9 GFLOPS: 61.98/242.17 result: MeasureResult(costs=(0.00373492735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7704739570617676, timestamp=1680316967.8509436) [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6267951
+ No: 10 GFLOPS: 157.19/242.17 result: MeasureResult(costs=(0.0014727039857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.386355876922607, timestamp=1680316968.709615) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8814443
+ No: 11 GFLOPS: 19.96/242.17 result: MeasureResult(costs=(0.011595925222222222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.137821912765503, timestamp=1680316969.6179323) [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3687793
+ No: 12 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1804,8 +906,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,84242
- No: 14 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,378493
+ No: 13 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1927,9 +1029,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,47837
- No: 15 GFLOPS: 18.97/18.97 result: MeasureResult(costs=(0.012202183111111112,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7925684452056885, timestamp=1680264187.0836403) [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3405610
- No: 16 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6133572
+ No: 14 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2051,8 +1152,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 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,653557
- No: 17 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,149371
+ No: 15 GFLOPS: 2.71/242.17 result: MeasureResult(costs=(0.08546508775,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.6383960247039795, timestamp=1680316974.4706283) [('tile_f', [-1, 4, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3874167
+ No: 16 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2174,8 +1276,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5064228
- No: 18 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+ 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, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6063187
+ No: 17 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2297,8 +1399,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('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,9201362
- No: 19 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2161915
+ No: 18 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2420,8 +1522,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10398817
- No: 20 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6218501
+ No: 19 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2543,7 +1645,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2342024
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9929413
+ No: 20 GFLOPS: 6.85/242.17 result: MeasureResult(costs=(0.033783313749999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.29587197303772, timestamp=1680316982.025626) [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5101067
@@ -2598,9 +1701,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3405610
+ [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7012841
Finish loading 20 records
- Time cost of this operator: 0.012520
+ Time cost of this operator: 0.001341
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 5a0eec34eb..fe3af6bb7d 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -360,10 +360,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.1 98.75 (1, 2, 10, 10, 3) 2 1 [316.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.04 0.95 (1, 6, 10, 10) 1 1 [3.04]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.301 (1, 1, 10, 10, 3) 1 1 [0.962]
- Total_time - 320.102 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 318.1 98.744 (1, 2, 10, 10, 3) 2 1 [318.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.957 (1, 6, 10, 10) 1 1 [3.082]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.299 (1, 1, 10, 10, 3) 1 1 [0.963]
+ Total_time - 322.145 - - - - -
@@ -428,10 +428,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.6 97.501 (1, 6, 10, 10, 1) 2 1 [103.6]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.797 1.691 (1, 6, 10, 10) 1 1 [1.797]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.858 0.807 (1, 3, 10, 10, 1) 1 1 [0.858]
- Total_time - 106.255 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.3 97.483 (1, 6, 10, 10, 1) 2 1 [103.3]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.805 1.703 (1, 6, 10, 10) 1 1 [1.805]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.862 0.814 (1, 3, 10, 10, 1) 1 1 [0.862]
+ Total_time - 105.967 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.086 seconds)
+ **Total running time of the script:** ( 1 minutes 19.858 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 4701a1909c..94b5dcd529 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -118,7 +118,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 10.1MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 16.1MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 20.0MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 30.6MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.317 seconds)
+ **Total running time of the script:** ( 1 minutes 17.127 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 476afec3b8..5bc06468de 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
@@ -217,7 +217,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp8juwrav6/images/random'
+ '/tmp/tmphyq_bic6/images/random'
@@ -308,7 +308,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -317,8 +317,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp8juwrav6/images/target contains 8144 images
- /tmp/tmp8juwrav6/images/random contains 5000 images
+ /tmp/tmphyq_bic6/images/target contains 8144 images
+ /tmp/tmphyq_bic6/images/random contains 5000 images
@@ -493,13 +493,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 41s - loss: 0.2104 - accuracy: 0.9288 - val_loss: 0.1292 - val_accuracy: 0.9558 - 41s/epoch - 124ms/step
+ 328/328 - 41s - loss: 0.2032 - accuracy: 0.9299 - val_loss: 0.2038 - val_accuracy: 0.9332 - 41s/epoch - 125ms/step
Epoch 2/3
- 328/328 - 35s - loss: 0.0861 - accuracy: 0.9693 - val_loss: 0.1373 - val_accuracy: 0.9524 - 35s/epoch - 106ms/step
+ 328/328 - 34s - loss: 0.0977 - accuracy: 0.9626 - val_loss: 0.0982 - val_accuracy: 0.9660 - 34s/epoch - 105ms/step
Epoch 3/3
- 328/328 - 35s - loss: 0.0574 - accuracy: 0.9792 - val_loss: 0.1309 - val_accuracy: 0.9566 - 35s/epoch - 105ms/step
+ 328/328 - 34s - loss: 0.0661 - accuracy: 0.9748 - val_loss: 0.0865 - val_accuracy: 0.9709 - 34s/epoch - 104ms/step
- <keras.callbacks.History object at 0x7fa5e3345a90>
+ <keras.callbacks.History object at 0x7fa7e9342cd0>
@@ -860,7 +860,7 @@ 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 33.391 seconds)
+ **Total running time of the script:** ( 4 minutes 22.010 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 b4290bc0c4..b4a484bb09 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
Computation times
=================
-**07:42.021** total execution time for **how_to_work_with_microtvm** files:
+**07:24.587** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:33.391 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:22.010 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:23.086 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:19.858 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:19.317 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:17.127 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.515 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.266 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:08.050 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:07.882 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.661 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.444 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 865e3277b0..9aacb200fe 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
=================
-**00:37.417** total execution time for **how_to_work_with_relay** files:
+**00:36.366** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.684 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.847 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:02.910 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:02.848 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.817 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.665 | 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 |
+| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 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 1a73778844..d826e81a24 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7fa37b7170e0>
+ <function my_cuda_math_rule at 0x7fa43a61b0e0>
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 ca68eae14e..ea3b468fa6 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
=================
-**00:09.451** total execution time for **how_to_work_with_schedules** files:
+**00:08.712** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.477 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.950 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.447 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.275 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.637 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.612 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.611 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.599 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.129 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.128 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.064 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.063 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.055 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.054 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.030 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 7b57234e44..98c217d94d 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:31.522** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:30.556** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.516 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:30.550 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index feca2a1b98..a1ccc42057 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 33.62s!
+ resnet18_v1 inference graph built in 32.56s!
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 862a2a56cf..b0161620a2 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 22.98s!
+ yolov3-tiny inference graph built in 22.28s!
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 2bd5dbe59f..bd3d768fce 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
=================
-**01:40.749** total execution time for **topic_vta_tutorials_frontend** files:
+**01:38.779** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.469 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.436 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.279 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.343 | 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 515a407102..9f2812be7d 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
=================
-**00:03.188** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.174** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.703 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.707 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.484 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.468 | 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 e5fd78a521..4338584711 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
=================
-**00:00.825** total execution time for **topic_vta_tutorials** files:
+**00:00.799** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.426 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.412 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.399 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.387 | 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 e33a6af9c0..9791d159fd 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,6 +207,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ .T
+
+
@@ -318,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.841 ms
+ Execution time of this operator: 94.480 ms
@@ -434,7 +441,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 35.957 seconds)
+ **Total running time of the script:** ( 1 minutes 31.657 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 6604a32612..5b31dafb64 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 12.58/12.58 result: MeasureResult(costs=(0.0213354186,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6930179595947266, timestamp=1680262472.2431269) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
- No: 2 GFLOPS: 1.53/12.58 result: MeasureResult(costs=(0.17585374380000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0729477405548096, timestamp=1680262475.3201342) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
- No: 3 GFLOPS: 11.77/12.58 result: MeasureResult(costs=(0.0228077934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7097334861755371, timestamp=1680262477.2220645) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 0.51/12.58 result: MeasureResult(costs=(0.5274926004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.664091348648071, timestamp=1680262487.1920028) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
- No: 5 GFLOPS: 3.32/12.58 result: MeasureResult(costs=(0.0808814766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5575499534606934, timestamp=1680262490.4692483) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
- No: 6 GFLOPS: 4.37/12.58 result: MeasureResult(costs=(0.0614117778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2563884258270264, timestamp=1680262491.711772) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
- No: 7 GFLOPS: 14.56/14.56 result: MeasureResult(costs=(0.018437087600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9013512134552002, timestamp=1680262492.267989) [('tile_y', [-1, 64]), ('tile_x', [-1, 64])],None,66
- No: 8 GFLOPS: 12.10/14.56 result: MeasureResult(costs=(0.0221832424,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7399411201477051, timestamp=1680262492.8867397) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
- No: 9 GFLOPS: 3.13/14.56 result: MeasureResult(costs=(0.0857591424,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.582322359085083, timestamp=1680262494.5826154) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
- No: 10 GFLOPS: 1.50/14.56 result: MeasureResult(costs=(0.1792620768,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.036386251449585, timestamp=1680262497.6711853) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 1 GFLOPS: 3.07/3.07 result: MeasureResult(costs=(0.0875686056,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6519381999969482, timestamp=1680315287.6446161) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 2 GFLOPS: 10.85/10.85 result: MeasureResult(costs=(0.0247445388,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6787183284759521, timestamp=1680315289.5259745) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+ No: 3 GFLOPS: 8.94/10.85 result: MeasureResult(costs=(0.03003245,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7182004451751709, timestamp=1680315290.262789) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+ No: 4 GFLOPS: 0.51/10.85 result: MeasureResult(costs=(0.5248235898,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.634685754776001, timestamp=1680315300.141615) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
+ No: 5 GFLOPS: 12.70/12.70 result: MeasureResult(costs=(0.0211389882,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6035053730010986, timestamp=1680315300.9063146) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
+ No: 6 GFLOPS: 11.89/12.70 result: MeasureResult(costs=(0.0225691456,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6688330173492432, timestamp=1680315301.526111) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 7 GFLOPS: 10.27/12.70 result: MeasureResult(costs=(0.026147772200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.655611515045166, timestamp=1680315303.4412062) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
+ No: 8 GFLOPS: 1.54/12.70 result: MeasureResult(costs=(0.1745465388,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.03352952003479, timestamp=1680315306.4876146) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+ No: 9 GFLOPS: 0.88/12.70 result: MeasureResult(costs=(0.3044655076,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.083791017532349, timestamp=1680315311.6972497) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+ No: 10 GFLOPS: 3.33/12.70 result: MeasureResult(costs=(0.080644848,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5073270797729492, timestamp=1680315313.2437055) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 1dacd57e32..fc1e616217 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
.. code-block:: none
- {'mean': 512.6999624700011, 'median': 512.9441132000068, 'std': 1.2014829374162335}
+ {'mean': 509.58684035999795, 'median': 508.9386698999931, 'std': 2.6515574204392656}
@@ -545,31 +545,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 11.14/ 23.29 GFLOPS | Progress: (4/20) | 10.40 s
[Task 1/25] Current/Best: 9.71/ 23.29 GFLOPS | Progress: (8/20) | 17.54 s
[Task 1/25] Current/Best: 14.24/ 23.29 GFLOPS | Progress: (12/20) | 20.19 s
[Task 1/25] Current/Best: 11.33/ 23.29 GFLOPS | Progress: (16/20) | 22.43 s
[Task 1/25] Current/Best: 7.39/ 23.29 GFLOPS | Progress: (20/20) | 28.77 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 17.33/ 18.41 GFLOPS | Progress: (4/20) | 4.54 s
[Task 2/25] Current/Best: 5.08/ 22.19 GFLOPS | Progress: (8/20) | 6.60 s
[Task 2/25] Current/Best: 17.40/ 22.19 GFLOPS | Progress: (12/20) | 8.28 s
[Task 2/25] Current/Best: 16.17/ 22.19 GFLOPS | Progress: (16/20) | 10.42 s
[Task 2/25] Current/Best: 10.55/ 22.19 GFLOPS | Progress: (20/20) | 13.51 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.85/ 14.43 GFLOPS | Progress: (4/20) | 5.58 s
[Task 3/25] Current/Best: 11.64/ 15.85 GFLOPS | Progress: (8/20) | 8.02 s
[Task 3/25] Current/Best: 12.73/ 22.01 GFLOPS | Progress: (12/20) | 10.42 s
[Task 3/25] Current/Best: 6.92/ 22.01 GFLOPS | Progress: (16/20) | 12.99 s
[Task 3/25] Current/Best: 11.16/ 22.01 GFLOPS | Progress: (20/20) | 15.23 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 18.11/ 18.11 GFLOPS | Progress: (4/20) | 5.35 s
[Task 4/25] Current/Best: 13.31/ 18.11 GFLOPS | Progress: (8/20) | 7.28 s
[Task 4/25] Current/Best: 10.42/ 18.11 GFLOPS | Progress: (12/20) | 9.59 s
[Task 4/25] Current/Best: 14.34/ 18.11 GFLOPS | Progress: (16/20) | 11.57 s
[Task 4/25] Current/Best: 6.14/ 18.11 GFLOPS | Progress: (20/20) | 17.02 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 15.99/ 19.41 GFLOPS | Progress: (4/20) | 5.15 s
[Task 5/25] Current/Best: 11.45/ 19.41 GFLOPS | Progress: (8/20) | 7.20 s
[Task 5/25] Current/Best: 8.13/ 19.41 GFLOPS | Progress: (12/20) | 9.11 s
[Task 5/25] Current/Best: 10.98/ 21.60 GFLOPS | Progress: (16/20) | 11.27 s
[Task 5/25] Current/Best: 11.56/ 21.60 GFLOPS | Progress: (20/20) | 13.91 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 7.04/ 17.47 GFLOPS | Progress: (4/20) | 5.92 s
[Task 6/25] Current/Best: 11.08/ 17.47 GFLOPS | Progress: (8/20) | 12.03 s
[Task 6/25] Current/Best: 14.69/ 17.47 GFLOPS | Progress: (12/20) | 15.72 s
[Task 6/25] Current/Best: 10.08/ 17.47 GFLOPS | Progress: (16/20) | 18.31 s
[Task 6/25] Current/Best: 9.68/ 22.51 GFLOPS | Progress: (20/20) | 25.78 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 21.11/ 21.11 GFLOPS | Progress: (4/20) | 4.71 s
[Task 7/25] Current/Best: 18.09/ 21.11 GFLOPS | Progress: (8/20) | 6.90 s
[Task 7/25] Current/Best: 11.91/ 21.11 GFLOPS | Progress: (12/20) | 9.41 s
[Task 7/25] Current/Best: 7.82/ 21.11 GFLOPS | Progress: (16/20) | 12.90 s
[Task 7/25] Current/Best: 18.85/ 21.11 GFLOPS | Progress: (20/20) | 15.55 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 12.08/ 18.01 GFLOPS | Progress: (4/20) | 6.32 s
[Task 8/25] Current/Best: 18.12/ 18.12 GFLOPS | Progress: (8/20) | 15.11 s
[Task 8/25] Current/Best: 8.67/ 18.12 GFLOPS | Progress: (12/20) | 19.06 s
[Task 8/25] Current/Best: 3.99/ 18.12 GFLOPS | Progress: (16/20) | 25.27 s
[Task 8/25] Current/Best: 3.59/ 18.12 GFLOPS | Progress: (20/20) | 31.39 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 8.48/ 22.77 GFLOPS | Progress: (4/20) | 10.66 s
[Task 9/25] Current/Best: 16.51/ 22.77 GFLOPS | Progress: (8/20) | 18.28 s
[Task 9/25] Current/Best: 9.93/ 22.77 GFLOPS | Progress: (12/20) | 29.47 s
[Task 9/25] Current/Best: 17.14/ 22.77 GFLOPS | Progress: (16/20) | 32.36 s
[Task 9/25] Current/Best: 17.78/ 22.77 GFLOPS | Progress: (20/20) | 34.66 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 4.20/ 14.36 GFLOPS | Progress: (4/20) | 4.83 s Done.
-
[Task 10/25] Current/Best: 14.08/ 14.36 GFLOPS | Progress: (8/20) | 7.14 s
[Task 10/25] Current/Best: 8.33/ 18.36 GFLOPS | Progress: (12/20) | 8.75 s
[Task 10/25] Current/Best: 12.15/ 18.36 GFLOPS | Progress: (16/20) | 10.33 s
[Task 10/25] Current/Best: 10.22/ 18.36 GFLOPS | Progress: (20/20) | 12.33 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 18.02/ 18.02 GFLOPS | Progress: (4/20) | 5.32 s
[Task 11/25] Current/Best: 15.86/ 23.35 GFLOPS | Progress: (8/20) | 7.84 s
[Task 11/25] Current/Best: 12.32/ 23.35 GFLOPS | Progress: (12/20) | 10.11 s
[Task 11/25] Current/Best: 13.08/ 23.35 GFLOPS | Progress: (16/20) | 12.67 s
[Task 11/25] Current/Best: 6.18/ 23.35 GFLOPS | Progress: (20/20) | 15.67 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 18.20/ 18.86 GFLOPS | Progress: (4/20) | 5.51 s
[Task 12/25] Current/Best: 10.70/ 20.26 GFLOPS | Progress: (8/20) | 12.03 s
[Task 12/25] Current/Best: 9.49/ 20.26 GFLOPS | Progress: (12/20) | 21.63 s
[Task 12/25] Current/Best: 17.66/ 20.26 GFLOPS | Progress: (16/20) | 24.30 s
[Task 12/25] Current/Best: 10.25/ 20.26 GFLOPS | Progress: (20/20) | 32.28 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (4/20) | 6.87 s
[Task 13/25] Current/Best: 8.12/ 23.46 GFLOPS | Progress: (8/20) | 9.46 s
[Task 13/25] Current/Best: 15.13/ 23.46 GFLOPS | Progress: (12/20) | 13.50 s
[Task 13/25] Current/Best: 9.13/ 23.46 GFLOPS | Progress: (16/20) | 17.43 s
[Task 13/25] Current/Best: 12.01/ 23.46 GFLOPS | Progress: (20/20) | 19.70 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 15.28/ 15.28 GFLOPS | Progress: (4/20) | 5.59 s
[Task 14/25] Current/Best: 12.96/ 15.28 GFLOPS | Progress: (8/20) | 11.00 s
[Task 14/25] Current/Best: 14.32/ 15.28 GFLOPS | Progress: (12/20) | 14.33 s
[Task 14/25] Current/Best: 16.81/ 21.33 GFLOPS | Progress: (16/20) | 18.09 s
[Task 14/25] Current/Best: 16.86/ 21.33 GFLOPS | Progress: (20/20) | 20.37 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 22.96/ 22.96 GFLOPS | Progress: (4/20) | 4.44 s
[Task 15/25] Current/Best: 5.49/ 22.96 GFLOPS | Progress: (8/20) | 8.45 s
[Task 15/25] Current/Best: 16.25/ 22.96 GFLOPS | Progress: (12/20) | 12.66 s
[Task 15/25] Current/Best: 11.68/ 22.96 GFLOPS | Progress: (16/20) | 15.02 s
[Task 15/25] Current/Best: 19.45/ 22.96 GFLOPS | Progress: (20/2
0) | 17.81 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 6.37/ 22.16 GFLOPS | Progress: (4/20) | 10.83 s
[Task 1/25] Current/Best: 7.04/ 22.16 GFLOPS | Progress: (8/20) | 15.53 s
[Task 1/25] Current/Best: 14.25/ 24.12 GFLOPS | Progress: (12/20) | 18.02 s
[Task 1/25] Current/Best: 11.56/ 24.12 GFLOPS | Progress: (16/20) | 20.57 s
[Task 1/25] Current/Best: 15.09/ 24.12 GFLOPS | Progress: (20/20) | 22.73 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 16.64/ 18.19 GFLOPS | Progress: (4/20) | 4.24 s
[Task 2/25] Current/Best: 17.61/ 18.19 GFLOPS | Progress: (8/20) | 5.67 s
[Task 2/25] Current/Best: 16.60/ 18.19 GFLOPS | Progress: (12/20) | 7.54 s
[Task 2/25] Current/Best: 12.16/ 18.19 GFLOPS | Progress: (16/20) | 9.30 s
[Task 2/25] Current/Best: 19.62/ 19.62 GFLOPS | Progress: (20/20) | 10.64 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 9.98/ 15.77 GFLOPS | Progress: (4/20) | 5.25 s
[Task 3/25] Current/Best: 14.87/ 24.24 GFLOPS | Progress: (8/20) | 7.12 s
[Task 3/25] Current/Best: 22.50/ 24.24 GFLOPS | Progress: (12/20) | 10.50 s
[Task 3/25] Current/Best: 1.62/ 24.24 GFLOPS | Progress: (16/20) | 14.25 s
[Task 3/25] Current/Best: 8.21/ 24.24 GFLOPS | Progress: (20/20) | 16.91 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 21.83/ 21.83 GFLOPS | Progress: (4/20) | 4.53 s
[Task 4/25] Current/Best: 16.83/ 21.83 GFLOPS | Progress: (8/20) | 9.26 s
[Task 4/25] Current/Best: 15.40/ 21.83 GFLOPS | Progress: (12/20) | 11.88 s
[Task 4/25] Current/Best: 13.08/ 21.83 GFLOPS | Progress: (16/20) | 15.87 s
[Task 4/25] Current/Best: 3.91/ 21.83 GFLOPS | Progress: (20/20) | 17.87 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 5.67/ 18.50 GFLOPS | Progress: (4/20) | 4.80 s
[Task 5/25] Current/Best: 15.71/ 19.80 GFLOPS | Progress: (8/20) | 6.91 s
[Task 5/25] Current/Best: 4.16/ 19.80 GFLOPS | Progress: (12/20) | 9.08 s
[Task 5/25] Current/Best: 11.40/ 19.80 GFLOPS | Progress: (16/20) | 11.48 s
[Task 5/25] Current/Best: 14.70/ 19.80 GFLOPS | Progress: (20/20) | 14.11 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.76/ 15.51 GFLOPS | Progress: (4/20) | 5.96 s
[Task 6/25] Current/Best: 15.44/ 15.51 GFLOPS | Progress: (8/20) | 9.27 s
[Task 6/25] Current/Best: 7.51/ 15.51 GFLOPS | Progress: (12/20) | 12.40 s
[Task 6/25] Current/Best: 11.81/ 18.30 GFLOPS | Progress: (16/20) | 14.43 s
[Task 6/25] Current/Best: 17.16/ 18.30 GFLOPS | Progress: (20/20) | 17.75 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 7.06/ 16.92 GFLOPS | Progress: (4/20) | 6.03 s
[Task 7/25] Current/Best: 11.88/ 21.43 GFLOPS | Progress: (8/20) | 8.87 s
[Task 7/25] Current/Best: 15.94/ 21.43 GFLOPS | Progress: (12/20) | 11.27 s
[Task 7/25] Current/Best: 19.51/ 21.43 GFLOPS | Progress: (16/20) | 13.29 s
[Task 7/25] Current/Best: 15.06/ 21.43 GFLOPS | Progress: (20/20) | 16.59 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.57/ 14.25 GFLOPS | Progress: (4/20) | 5.54 s
[Task 8/25] Current/Best: 10.44/ 16.87 GFLOPS | Progress: (8/20) | 11.05 s
[Task 8/25] Current/Best: 9.75/ 18.27 GFLOPS | Progress: (12/20) | 14.29 s
[Task 8/25] Current/Best: 18.52/ 18.52 GFLOPS | Progress: (16/20) | 17.80 s
[Task 8/25] Current/Best: 4.56/ 18.52 GFLOPS | Progress: (20/20) | 21.63 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 7.11/ 15.16 GFLOPS | Progress: (4/20) | 8.12 s
[Task 9/25] Current/Best: 15.68/ 18.80 GFLOPS | Progress: (8/20) | 10.09 s
[Task 9/25] Current/Best: 12.97/ 18.80 GFLOPS | Progress: (12/20) | 21.21 s
[Task 9/25] Current/Best: 6.47/ 18.80 GFLOPS | Progress: (16/20) | 29.26 s
[Task 9/25] Current/Best: 10.58/ 18.80 GFLOPS | Progress: (20/20) | 34.82 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 8.25/ 19.34 GFLOPS | Progress: (4/20) | 4.77 s Done.
+
[Task 10/25] Current/Best: 6.03/ 20.66 GFLOPS | Progress: (8/20) | 6.54 s
[Task 10/25] Current/Best: 13.74/ 20.66 GFLOPS | Progress: (12/20) | 8.18 s
[Task 10/25] Current/Best: 16.48/ 20.66 GFLOPS | Progress: (16/20) | 10.12 s
[Task 10/25] Current/Best: 18.11/ 21.59 GFLOPS | Progress: (20/20) | 12.32 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 18.00/ 18.59 GFLOPS | Progress: (4/20) | 4.77 s
[Task 11/25] Current/Best: 22.31/ 22.31 GFLOPS | Progress: (8/20) | 7.48 s
[Task 11/25] Current/Best: 14.88/ 22.31 GFLOPS | Progress: (12/20) | 9.86 s
[Task 11/25] Current/Best: 16.00/ 22.31 GFLOPS | Progress: (16/20) | 12.81 s
[Task 11/25] Current/Best: 6.94/ 22.31 GFLOPS | Progress: (20/20) | 15.51 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 10.64/ 16.00 GFLOPS | Progress: (4/20) | 5.89 s
[Task 12/25] Current/Best: 10.15/ 16.00 GFLOPS | Progress: (8/20) | 12.00 s
[Task 12/25] Current/Best: 10.82/ 16.00 GFLOPS | Progress: (12/20) | 14.20 s
[Task 12/25] Current/Best: 4.47/ 16.00 GFLOPS | Progress: (16/20) | 16.65 s
[Task 12/25] Current/Best: 12.44/ 18.18 GFLOPS | Progress: (20/20) | 22.29 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 10.76/ 14.70 GFLOPS | Progress: (4/20) | 6.49 s
[Task 13/25] Current/Best: 5.17/ 21.53 GFLOPS | Progress: (8/20) | 9.56 s
[Task 13/25] Current/Best: 23.21/ 23.21 GFLOPS | Progress: (12/20) | 12.28 s
[Task 13/25] Current/Best: 13.29/ 23.21 GFLOPS | Progress: (16/20) | 14.66 s
[Task 13/25] Current/Best: 18.27/ 23.21 GFLOPS | Progress: (20/20) | 16.86 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 5.44/ 16.41 GFLOPS | Progress: (4/20) | 5.42 s
[Task 14/25] Current/Best: 3.98/ 17.85 GFLOPS | Progress: (8/20) | 10.39 s
[Task 14/25] Current/Best: 11.97/ 17.85 GFLOPS | Progress: (12/20) | 12.90 s
[Task 14/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (16/20) | 15.19 s
[Task 14/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (20/20) | 17.68 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 15.94/ 15.94 GFLOPS | Progress: (4/20) | 7.07 s
[Task 15/25] Current/Best: 18.47/ 18.47 GFLOPS | Progress: (8/20) | 8.96 s
[Task 15/25] Current/Best: 13.48/ 18.47 GFLOPS | Progress: (12/20) | 12.74 s
[Task 15/25] Current/Best: 15.36/ 18.47 GFLOPS | Progress: (16/20) | 18.47 s
[Task 15/25] Current/Best: 18.46/ 18.47 GFLOPS | Progress: (20/2
0) | 21.25 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 15.21/ 20.71 GFLOPS | Progress: (4/20) | 5.57 s
[Task 16/25] Current/Best: 13.30/ 20.71 GFLOPS | Progress: (8/20) | 7.48 s
[Task 16/25] Current/Best: 10.34/ 20.71 GFLOPS | Progress: (12/20) | 10.30 s
[Task 16/25] Current/Best: 19.61/ 20.71 GFLOPS | Progress: (16/20) | 12.30 s
[Task 16/25] Current/Best: 16.79/ 20.71 GFLOPS | Progress: (20/20) | 14.87 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 24.06/ 24.06 GFLOPS | Progress: (4/20) | 5.27 s
[Task 17/25] Current/Best: 20.42/ 24.06 GFLOPS | Progress: (8/20) | 7.24 s
[Task 17/25] Current/Best: 20.85/ 24.06 GFLOPS | Progress: (12/20) | 9.25 s
[Task 17/25] Current/Best: 4.57/ 24.06 GFLOPS | Progress: (16/20) | 12.02 s
[Task 17/25] Current/Best: 5.22/ 24.06 GFLOPS | Progress: (20/20) | 14.74 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 9.54/ 14.70 GFLOPS | Progress: (4/20) | 5.51 s
[Task 18/25] Current/Best: 4.22/ 17.42 GFLOPS | Progress: (8/20) | 11.65 s
[Task 18/25] Current/Best: 17.73/ 17.73 GFLOPS | Progress: (12/20) | 14.01 s
[Task 18/25] Current/Best: 13.22/ 17.73 GFLOPS | Progress: (16/20) | 16.56 s
[Task 18/25] Current/Best: 8.88/ 17.73 GFLOPS | Progress: (20/20) | 22.20 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 21.36/ 21.36 GFLOPS | Progress: (4/20) | 6.94 s
[Task 19/25] Current/Best: 18.28/ 21.36 GFLOPS | Progress: (8/20) | 10.61 s Done.
Done.
-
[Task 16/25] Current/Best: 7.44/ 15.28 GFLOPS | Progress: (4/20) | 4.78 s
[Task 16/25] Current/Best: 9.46/ 15.28 GFLOPS | Progress: (8/20) | 7.17 s
[Task 16/25] Current/Best: 10.65/ 21.04 GFLOPS | Progress: (12/20) | 8.97 s
[Task 16/25] Current/Best: 6.13/ 21.04 GFLOPS | Progress: (16/20) | 10.60 s
[Task 16/25] Current/Best: 16.32/ 21.04 GFLOPS | Progress: (20/20) | 13.78 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.90/ 15.25 GFLOPS | Progress: (4/20) | 5.36 s
[Task 17/25] Current/Best: 13.14/ 15.25 GFLOPS | Progress: (8/20) | 8.06 s
[Task 17/25] Current/Best: 10.04/ 22.50 GFLOPS | Progress: (12/20) | 10.56 s
[Task 17/25] Current/Best: 9.28/ 22.50 GFLOPS | Progress: (16/20) | 13.92 s
[Task 17/25] Current/Best: 19.61/ 22.50 GFLOPS | Progress: (20/20) | 16.20 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.33/ 17.81 GFLOPS | Progress: (4/20) | 5.49 s
[Task 18/25] Current/Best: 15.28/ 17.81 GFLOPS | Progress: (8/20) | 13.69 s
[Task 18/25] Current/Best: 15.46/ 17.81 GFLOPS | Progress: (12/20) | 16.80 s
[Task 18/25] Current/Best: 17.28/ 17.81 GFLOPS | Progress: (16/20) | 19.61 s
[Task 18/25] Current/Best: 8.46/ 19.69 GFLOPS | Progress: (20/20) | 25.22 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 5.25/ 18.67 GFLOPS | Progress: (4/20) | 5.88 s
[Task 19/25] Current/Best: 5.28/ 18.67 GFLOPS | Progress: (8/20) | 9.01 s
[Task 19/25] Current/Best: 10.38/ 21.72 GFLOPS | Progress: (12/20) | 11.35 s
[Task 19/25] Current/Best: 18.11/ 21.72 GFLOPS | Progress: (16/20) | 13.80 s
[Task 19/25] Current/Best: 1.55/ 21.72 GFLOPS | Progress: (20/20) | 19.32 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 6.86/ 15.80 GFLOPS | Progress: (4/20) | 4.89 s
[Task 20/25] Current/Best: 10.68/ 15.80 GFLOPS | Progress: (8/20) | 8.45 s
[Task 20/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (12/20) | 12.79 s
[Task 20/25] Current/Best: 7.54/ 20.66 GFLOPS | Progress: (16/20) | 16.90 s
[Task 20/25] Current/Best: 15.16/ 20.66 GFLOPS | Progress: (20/20) | 19.94 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 14.32/ 18.18 GFLOPS | Progress: (4/20) | 5.64 s Done.
-
[Task 21/25] Current/Best: 22.55/ 22.55 GFLOPS | Progress: (8/20) | 7.49 s
[Task 21/25] Current/Best: 19.48/ 22.55 GFLOPS | Progress: (12/20) | 10.37 s
[Task 21/25] Current/Best: 2.72/ 22.55 GFLOPS | Progress: (16/20) | 14.26 s
[Task 21/25] Current/Best: 16.97/ 22.55 GFLOPS | Progress: (20/20) | 18.73 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 14.37/ 14.37 GFLOPS | Progress: (4/20) | 6.41 s
[Task 22/25] Current/Best: 12.89/ 14.37 GFLOPS | Progress: (8/20) | 8.88 s
[Task 22/25] Current/Best: 12.20/ 18.31 GFLOPS | Progress: (12/20) | 10.74 s
[Task 22/25] Current/Best: 2.66/ 20.97 GFLOPS | Progress: (16/20) | 12.89 s
[Task 22/25] Current/Best: 10.02/ 20.97 GFLOPS | Progress: (20/20) | 14.65 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 9.57/ 21.58 GFLOPS | Progress: (4/20) | 5.95 s
[Task 23/25] Current/Best: 1.55/ 21.58 GFLOPS | Progress: (8/20) | 10.16 s
[Task 23/25] Current/Best: 11.27/ 21.58 GFLOPS | Progress: (12/20) | 12.52 s
[Task 23/25] Current/Best: 21.78/ 21.78 GFLOPS | Progress: (16/20) | 14.71 s
[Task 23/25] Current/Best: 6.14/ 22.48 GFLOPS | Progress: (20/20) | 17.62 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.30/ 9.58 GFLOPS | Progress: (4/20) | 13.84 s
[Task 24/25] Current/Best: 9.40/ 9.58 GFLOPS | Progress: (8/20) | 24.81 s
[Task 24/25] Current/Best: 6.25/ 9.58 GFLOPS | Progress: (12/20) | 27.57 s
[Task 24/25] Current/Best: 5.11/ 9.58 GFLOPS | Progress: (16/20) | 37.95 s
[Task 24/25] Current/Best: 9.23/ 9.58 GFLOPS | Progress: (20/20) | 50.51 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 19/25] Current/Best: 12.89/ 22.40 GFLOPS | Progress: (12/20) | 14.30 s
[Task 19/25] Current/Best: 19.24/ 22.40 GFLOPS | Progress: (16/20) | 17.07 s
[Task 19/25] Current/Best: 9.31/ 22.40 GFLOPS | Progress: (20/20) | 19.54 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.62/ 13.04 GFLOPS | Progress: (4/20) | 5.18 s
[Task 20/25] Current/Best: 17.87/ 17.87 GFLOPS | Progress: (8/20) | 7.70 s
[Task 20/25] Current/Best: 12.66/ 17.87 GFLOPS | Progress: (12/20) | 11.12 s
[Task 20/25] Current/Best: 14.60/ 17.87 GFLOPS | Progress: (16/20) | 13.94 s
[Task 20/25] Current/Best: 6.17/ 18.06 GFLOPS | Progress: (20/20) | 16.21 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 2.73/ 17.99 GFLOPS | Progress: (4/20) | 5.17 s
[Task 21/25] Current/Best: 9.50/ 17.99 GFLOPS | Progress: (8/20) | 9.37 s
[Task 21/25] Current/Best: 7.19/ 19.80 GFLOPS | Progress: (12/20) | 12.45 s
[Task 21/25] Current/Best: 10.04/ 19.80 GFLOPS | Progress: (16/20) | 15.64 s
[Task 21/25] Current/Best: 2.47/ 19.80 GFLOPS | Progress: (20/20
) | 17.65 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 9.74/ 17.39 GFLOPS | Progress: (4/20) | 6.26 s Done.
Done.
-
[Task 25/25] Current/Best: 2.98/ 4.10 GFLOPS | Progress: (4/20) | 15.10 s
[Task 25/25] Current/Best: 1.55/ 7.84 GFLOPS | Progress: (8/20) | 27.08 s
[Task 25/25] Current/Best: 4.31/ 7.84 GFLOPS | Progress: (12/20) | 32.84 s
[Task 25/25] Current/Best: 8.30/ 8.30 GFLOPS | Progress: (16/20) | 34.87 s
[Task 25/25] Current/Best: 9.23/ 9.23 GFLOPS | Progress: (20/20) | 45.83 s
+
[Task 22/25] Current/Best: 7.49/ 17.39 GFLOPS | Progress: (8/20) | 8.46 s
[Task 22/25] Current/Best: 2.76/ 17.39 GFLOPS | Progress: (12/20) | 11.49 s
[Task 22/25] Current/Best: 9.87/ 18.82 GFLOPS | Progress: (16/20) | 14.43 s
[Task 22/25] Current/Best: 15.64/ 18.82 GFLOPS | Progress: (20/20) | 17.19 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 9.61/ 19.93 GFLOPS | Progress: (4/20) | 6.10 s
[Task 23/25] Current/Best: 21.79/ 21.79 GFLOPS | Progress: (8/20) | 10.12 s
[Task 23/25] Current/Best: 19.87/ 21.79 GFLOPS | Progress: (12/20) | 13.89 s
[Task 23/25] Current/Best: 8.82/ 21.79 GFLOPS | Progress: (16/20) | 16.80 s
[Task 23/25] Current/Best: 22.16/ 24.03 GFLOPS | Progress: (20/20) | 19.00 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.05/ 4.13 GFLOPS | Progress: (4/20) | 8.99 s
[Task 24/25] Current/Best: 3.84/ 7.18 GFLOPS | Progress: (8/20) | 12.36 s
[Task 24/25] Current/Best: 6.25/ 10.46 GFLOPS | Progress: (12/20) | 23.30 s
[Task 24/25] Current/Best: 3.75/ 10.46 GFLOPS | Progress: (16/20) | 34.28 s
[Task 24/25] Current/Best: 2.34/ 10.46 GFLOPS | Progress: (20/20) | 46.59 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 7.34/ 7.93 GFLOPS | Progress: (4/20) | 13.66 s Done.
+
[Task 25/25] Current/Best: 7.70/ 9.73 GFLOPS | Progress: (8/20) | 24.32 s
[Task 25/25] Current/Best: 3.04/ 9.73 GFLOPS | Progress: (12/20) | 36.90 s
[Task 25/25] Current/Best: 1.55/ 10.11 GFLOPS | Progress: (16/20) | 47.87 s
[Task 25/25] Current/Best: 2.53/ 10.11 GFLOPS | Progress: (20/20) | 58.83 s
@@ -665,8 +665,8 @@ 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
@@ -723,8 +723,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 398.90424599999733, 'median': 397.49282374999666, 'std': 3.5888206502880196}
- unoptimized: {'mean': 512.6999624700011, 'median': 512.9441132000068, 'std': 1.2014829374162335}
+ optimized: {'mean': 410.20361767999475, 'median': 408.73830729999554, 'std': 3.347262406241466}
+ unoptimized: {'mean': 509.58684035999795, 'median': 508.9386698999931, 'std': 2.6515574204392656}
@@ -747,7 +747,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 13 minutes 7.761 seconds)
+ **Total running time of the script:** ( 12 minutes 33.459 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 fec9d491ba..0010c2ab21 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.369e-07 secs/op
+ 1.485e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index d3687a6409..2e5df67eb6 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -270,7 +270,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x104a78f0)), stage(b, placeholder(b, 0x22dfe710)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T [...]
+ [stage(a, placeholder(a, 0xbcb9f50)), stage(b, placeholder(b, 0x229e9200)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 2bc0abacb0..f419ba5914 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**16:59.897** total execution time for **tutorial** files:
+**16:15.127** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 13:07.761 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:33.459 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:35.957 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:31.657 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:03.088 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:57.137 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:37.236 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.368 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:33.042 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:33.652 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.763 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.844 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.859 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.841 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.190 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.168 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 29b5b60cd7..7aa5d59d33 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -285,8 +285,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
- naive: 0.000007
+ Numpy running time: 0.000012
+ naive: 0.000009
@@ -444,7 +444,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000032
+ vector: 0.000025
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.367289999820059e-06 1.0
- naive 6.8297e-06 0.9270301562944869
- parallel 7.4248e-06 1.007806126836509
- vector 3.18535e-05 4.323638678642758
+ numpy 1.2035689999265741e-05 1.0
+ naive 8.8403e-06 0.734507120118524
+ parallel 6.9763000000000004e-06 0.5796344040454351
+ vector 2.45827e-05 2.0424836466791447
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018865
+ Numpy running time: 0.017709
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.568804
+ none: 3.088310
@@ -1080,7 +1080,7 @@ schedule.
.. code-block:: none
- blocking: 0.293213
+ blocking: 0.289019
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.332215
+ vectorization: 0.334241
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1230,7 +1230,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.119187
+ loop permutation: 0.113900
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1321,7 +1321,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109593
+ array packing: 0.108426
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1404,7 +1404,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111158
+ block caching: 0.110020
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1478,7 +1478,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.147267
+ parallelization: 0.145530
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1548,13 +1548,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.5688042943 1.0
- blocking 0.2932132598 0.0821600837760458
- vectorization 0.3322146373 0.09308849964975789
- loop permutation 0.1191874021 0.033397012632596014
- array packing 0.1095930104 0.030708607522984394
- block caching 0.1111575985 0.031147014331253182
- parallelization 0.1472671276 0.041265117236944364
+ none 3.0883096068 1.0
+ blocking 0.2890188348 0.09358479932310651
+ vectorization 0.3342410449 0.10822782928371259
+ loop permutation 0.11389982540000002 0.03688096075251311
+ array packing 0.1084264876 0.03510868449240352
+ block caching 0.11001961810000001 0.03562454290779432
+ parallelization 0.14552988640000003 0.04712282929132648
@@ -1594,11 +1594,6 @@ 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 3.088 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index b53b9b74ec..fe344d54c6 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-b724c87f76071c1c4d39c17aa0638bd94c878d61
+98007f90d8d60a77e997dc79c2cfc5d7e9c85ebb
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index bd834f1a00..28917b617c 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -590,7 +590,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.354 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.309 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index ac48be9951..e045a0a2ff 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -444,7 +444,7 @@
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipc6b04538-23f3-4d1b-9feb-d5fcfb06ed08 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.zip4b04227a-1808-458c-bcfc-7a49db732363 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 549728adfa..1d5e7335c5 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -454,13 +454,15 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 55.7MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 57.8MB/s]
- 48%|####7 | 19.9M/41.5M [00:00<00:00, 45.1MB/s]
- 59%|#####8 | 24.4M/41.5M [00:00<00:00, 35.1MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 36.4MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 39.2MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 40.8MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 63.4MB/s]
+ 30%|##9 | 12.4M/41.5M [00:00<00:00, 59.4MB/s]
+ 43%|####3 | 18.0M/41.5M [00:00<00:00, 42.4MB/s]
+ 54%|#####4 | 22.5M/41.5M [00:00<00:00, 41.4MB/s]
+ 64%|######4 | 26.6M/41.5M [00:00<00:00, 34.0MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 29.1MB/s]
+ 89%|########8 | 36.8M/41.5M [00:01<00:00, 33.5MB/s]
+ 97%|#########7| 40.4M/41.5M [00:01<00:00, 27.4MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 34.3MB/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 8c560c5b03..96f4cff23d 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -437,12 +437,11 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 78.2MB/s]
- 40%|#### | 18.1M/44.7M [00:00<00:00, 60.2MB/s]
- 54%|#####4 | 24.1M/44.7M [00:00<00:00, 45.3MB/s]
- 68%|######7 | 30.3M/44.7M [00:00<00:00, 41.8MB/s]
- 85%|########4 | 37.8M/44.7M [00:00<00:00, 50.7MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 54.3MB/s]
+ 32%|###2 | 14.3M/44.7M [00:00<00:00, 103MB/s]
+ 54%|#####4 | 24.1M/44.7M [00:00<00:00, 84.8MB/s]
+ 72%|#######2 | 32.2M/44.7M [00:00<00:00, 64.4MB/s]
+ 89%|########9 | 39.8M/44.7M [00:00<00:00, 68.6MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 69.7MB/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 dd9c2e7c7a..02b408ee0f 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -657,7 +657,7 @@ 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 32.713 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.163 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 67257e7c95..7994afed73 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:59.758</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:51.194</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:32.713</p></td>
+<td><p>01:31.163</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:22.354</p></td>
+<td><p>01:21.309</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:58.894</p></td>
+<td><p>00:57.132</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:38.824</p></td>
+<td><p>00:38.155</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:32.975</p></td>
+<td><p>00:31.883</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:30.674</p></td>
+<td><p>00:29.913</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>00:29.050</p></td>
+<td><p>00:28.917</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:26.926</p></td>
+<td><p>00:26.060</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>00:24.617</p></td>
+<td><p>00:23.946</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>00:02.731</p></td>
+<td><p>00:02.717</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno.html b/docs/how_to/deploy_models/deploy_model_on_adreno.html
index 5a4f679981..3603c4ac9d 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -799,9 +799,10 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2538.6539 2538.4716 2541.9388 2536.9734 1.4015
+ 3334.5961 3332.9302 3346.3906 3331.5372 4.1951
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.080 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/2387d8448da213eb625e6b3d916327d4/deploy_model_on_adreno.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_model_on_adreno.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
index b328effdff..9681c04534 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
@@ -443,28 +443,27 @@ to run this tutorial with a real device over rpc.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
8192/102967424 [..............................] - ETA: 0s
- 5701632/102967424 [>.............................] - ETA: 0s
8380416/102967424 [=>............................] - ETA: 1s
+ 15024128/102967424 [===>..........................] - ETA: 1s
16769024/102967424 [===>..........................] - ETA: 1s
- 23412736/102967424 [=====>........................] - ETA: 1s
25157632/102967424 [======>.......................] - ETA: 1s
- 31432704/102967424 [========>.....................] - ETA: 1s
- 33546240/102967424 [========>.....................] - ETA: 1s
+ 33546240/102967424 [========>.....................] - ETA: 0s
+ 40189952/102967424 [==========>...................] - ETA: 0s
41934848/102967424 [===========>..................] - ETA: 1s
- 48578560/102967424 [=============>................] - ETA: 0s
50323456/102967424 [=============>................] - ETA: 0s
- 50462720/102967424 [=============>................] - ETA: 1s
+ 52518912/102967424 [==============>...............] - ETA: 0s
+ 55746560/102967424 [===============>..............] - ETA: 0s
58712064/102967424 [================>.............] - ETA: 0s
- 65355776/102967424 [==================>...........] - ETA: 0s
67100672/102967424 [==================>...........] - ETA: 0s
69296128/102967424 [===================>..........] - ETA: 0s
72540160/102967424 [====================>.........] - ETA: 0s
75489280/102967424 [====================>.........] - ETA: 0s
- 82124800/102967424 [======================>.......] - ETA: 0s
83877888/102967424 [=======================>......] - ETA: 0s
90521600/102967424 [=========================>....] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
98910208/102967424 [===========================>..] - ETA: 0s
+100646912/102967424 [============================>.] - ETA: 0s
+101031936/102967424 [============================>.] - ETA: 0s
102850560/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 2s 0us/step
</pre></div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 9856a8271b..2096250090 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -667,7 +667,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3938 16.3993 16.8581 15.9140 0.4216
+ 15.8672 15.7627 16.7829 15.4190 0.3903
</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 1ae45bce87..84d60c8dbd 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -459,33 +459,38 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 4%|3 | 6.30M/170M [00:00<00:07, 22.9MB/s]
- 7%|6 | 11.5M/170M [00:00<00:04, 33.4MB/s]
- 9%|9 | 16.0M/170M [00:00<00:05, 29.3MB/s]
- 11%|#1 | 19.2M/170M [00:00<00:05, 29.6MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:04, 35.0MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:03, 38.9MB/s]
- 24%|##3 | 40.0M/170M [00:01<00:02, 47.3MB/s]
- 28%|##8 | 48.0M/170M [00:01<00:02, 54.0MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:01, 61.4MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:01, 57.6MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 59.8MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 57.1MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 53.2MB/s]
- 56%|#####5 | 94.3M/170M [00:02<00:02, 38.4MB/s]
- 58%|#####8 | 98.6M/170M [00:02<00:01, 37.8MB/s]
- 61%|######1 | 104M/170M [00:02<00:01, 34.6MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 41.4MB/s]
- 71%|####### | 120M/170M [00:02<00:01, 47.5MB/s]
- 75%|#######5 | 128M/170M [00:03<00:00, 47.1MB/s]
- 79%|#######9 | 134M/170M [00:03<00:00, 49.0MB/s]
- 82%|########1 | 139M/170M [00:03<00:00, 48.1MB/s]
- 85%|########4 | 144M/170M [00:03<00:00, 46.5MB/s]
- 88%|########8 | 150M/170M [00:03<00:00, 48.5MB/s]
- 91%|#########1| 155M/170M [00:03<00:00, 42.0MB/s]
- 94%|#########4| 160M/170M [00:03<00:00, 40.9MB/s]
- 99%|#########8| 168M/170M [00:03<00:00, 47.2MB/s]
-100%|##########| 170M/170M [00:03<00:00, 45.0MB/s]
+ 4%|3 | 6.30M/170M [00:00<00:04, 39.8MB/s]
+ 6%|5 | 10.1M/170M [00:00<00:05, 32.8MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:05, 27.7MB/s]
+ 10%|9 | 17.0M/170M [00:00<00:06, 26.0MB/s]
+ 13%|#3 | 22.3M/170M [00:00<00:04, 32.7MB/s]
+ 17%|#7 | 29.2M/170M [00:00<00:03, 43.1MB/s]
+ 20%|#9 | 33.6M/170M [00:01<00:05, 28.4MB/s]
+ 24%|##3 | 40.0M/170M [00:01<00:04, 32.2MB/s]
+ 27%|##7 | 46.3M/170M [00:01<00:03, 32.6MB/s]
+ 29%|##9 | 49.8M/170M [00:01<00:04, 28.3MB/s]
+ 33%|###2 | 56.0M/170M [00:01<00:03, 31.7MB/s]
+ 37%|###6 | 62.3M/170M [00:01<00:03, 37.0MB/s]
+ 39%|###8 | 66.2M/170M [00:02<00:03, 31.4MB/s]
+ 42%|####2 | 72.0M/170M [00:02<00:02, 35.0MB/s]
+ 46%|####6 | 78.3M/170M [00:02<00:02, 35.0MB/s]
+ 48%|####8 | 81.8M/170M [00:02<00:03, 29.7MB/s]
+ 52%|#####1 | 88.0M/170M [00:02<00:02, 30.0MB/s]
+ 57%|#####6 | 96.0M/170M [00:03<00:02, 37.2MB/s]
+ 60%|###### | 102M/170M [00:03<00:01, 43.1MB/s]
+ 63%|######2 | 107M/170M [00:03<00:01, 43.9MB/s]
+ 66%|######5 | 112M/170M [00:03<00:01, 41.0MB/s]
+ 71%|####### | 120M/170M [00:03<00:01, 40.9MB/s]
+ 75%|#######5 | 128M/170M [00:03<00:01, 42.5MB/s]
+ 79%|#######9 | 134M/170M [00:04<00:00, 38.0MB/s]
+ 81%|########1 | 138M/170M [00:04<00:00, 34.8MB/s]
+ 85%|########4 | 144M/170M [00:04<00:00, 31.4MB/s]
+ 88%|########8 | 150M/170M [00:04<00:00, 34.1MB/s]
+ 90%|######### | 154M/170M [00:04<00:00, 33.7MB/s]
+ 93%|#########3| 158M/170M [00:04<00:00, 35.4MB/s]
+ 95%|#########5| 162M/170M [00:04<00:00, 32.9MB/s]
+ 98%|#########7| 166M/170M [00:05<00:00, 34.1MB/s]
+100%|##########| 170M/170M [00:05<00:00, 34.6MB/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=& [...]
@@ -583,7 +588,7 @@ 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 40.580 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 31.281 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 2267131c94..5c50971d38 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -500,8 +500,9 @@ 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, 70.6MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 88.3MB/s]
+ 47%|####6 | 6.30M/13.6M [00:00<00:00, 55.6MB/s]
+ 86%|########5 | 11.6M/13.6M [00:00<00:00, 49.3MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 43.7MB/s]
</pre></div>
</div>
</div>
@@ -592,7 +593,7 @@ 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)
- 90.4813 90.4530 91.7494 90.0229 0.3207
+ 90.0886 90.0133 91.4481 89.8131 0.2543
</pre></div>
</div>
<div class="admonition note">
@@ -631,7 +632,7 @@ 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 17.322 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.570 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 a6fda96416..0667d90226 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -585,7 +585,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.3480 120.0775 126.6966 119.3052 1.1110
+ 117.5498 117.1134 122.2979 115.9022 1.3083
</pre></div>
</div>
<div class="admonition note">
@@ -613,7 +613,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 35.047 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.407 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 2ad1e8b337..bb7c9987fa 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -526,7 +526,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.444 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 51.012 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 3a10bfdfcd..1dc8b66173 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -468,24 +468,26 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 1%| | 1202/132723 [00:00<00:10, 11977.55KB/s]
- 3%|2 | 3778/132723 [00:00<00:06, 20055.49KB/s]
- 7%|7 | 9298/132723 [00:00<00:03, 36078.60KB/s]
- 13%|#2 | 16863/132723 [00:00<00:02, 51685.42KB/s]
- 18%|#8 | 24389/132723 [00:00<00:01, 60177.91KB/s]
- 25%|##4 | 32847/132723 [00:00<00:01, 68468.77KB/s]
- 31%|###1 | 41570/132723 [00:00<00:01, 74593.79KB/s]
- 38%|###7 | 50375/132723 [00:00<00:01, 78874.33KB/s]
- 44%|####4 | 59024/132723 [00:00<00:00, 81252.89KB/s]
- 51%|#####1 | 67871/132723 [00:01<00:00, 83477.87KB/s]
- 58%|#####7 | 76593/132723 [00:01<00:00, 84619.21KB/s]
- 64%|######4 | 85379/132723 [00:01<00:00, 85603.01KB/s]
- 71%|####### | 94101/132723 [00:01<00:00, 86088.35KB/s]
- 77%|#######7 | 102837/132723 [00:01<00:00, 86468.14KB/s]
- 84%|########4 | 111542/132723 [00:01<00:00, 86641.54KB/s]
- 91%|######### | 120393/132723 [00:01<00:00, 87199.92KB/s]
- 97%|#########7| 129114/132723 [00:01<00:00, 87189.04KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 76108.50KB/s]
+ 1%|1 | 1361/132723 [00:00<00:09, 13564.51KB/s]
+ 3%|3 | 4337/132723 [00:00<00:05, 23022.43KB/s]
+ 8%|8 | 10993/132723 [00:00<00:02, 42860.31KB/s]
+ 12%|#2 | 16506/132723 [00:00<00:02, 46920.89KB/s]
+ 18%|#8 | 24365/132723 [00:00<00:01, 58209.45KB/s]
+ 23%|##3 | 30828/132723 [00:00<00:01, 60374.52KB/s]
+ 28%|##7 | 36873/132723 [00:00<00:01, 50249.48KB/s]
+ 32%|###1 | 42161/132723 [00:00<00:01, 50777.97KB/s]
+ 37%|###6 | 48828/132723 [00:00<00:01, 55290.76KB/s]
+ 41%|####1 | 54531/132723 [00:01<00:01, 55518.88KB/s]
+ 48%|####7 | 63090/132723 [00:01<00:01, 64265.90KB/s]
+ 52%|#####2 | 69646/132723 [00:01<00:01, 51349.87KB/s]
+ 59%|#####8 | 77840/132723 [00:01<00:00, 58992.34KB/s]
+ 64%|######4 | 84961/132723 [00:01<00:00, 62204.26KB/s]
+ 71%|####### | 93677/132723 [00:01<00:00, 69019.86KB/s]
+ 76%|#######6 | 100928/132723 [00:01<00:00, 66187.94KB/s]
+ 83%|########2 | 109761/132723 [00:01<00:00, 72272.30KB/s]
+ 88%|########8 | 117228/132723 [00:02<00:00, 64378.96KB/s]
+ 95%|#########4| 126085/132723 [00:02<00:00, 70721.89KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 60273.32KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -524,7 +526,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 53.517 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 47.991 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 62483be819..1d990ca700 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>16:38.325</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>16:27.313</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:53.517</p></td>
+<td><p>03:47.991</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:40.580</p></td>
+<td><p>03:31.281</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:35.047</p></td>
+<td><p>02:28.407</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>01:42.444</p></td>
+<td><p>01:51.012</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>01:17.322</p></td>
+<td><p>01:15.570</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno™</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:55.238</p></td>
+<td><p>01:04.080</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_adreno_tvmc.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-tvmc-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno™ with tvmc Interface</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno_tvmc.py</span></code>)</p></td>
-<td><p>00:52.695</p></td>
+<td><p>00:51.543</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:43.600</p></td>
+<td><p>00:42.127</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:29.213</p></td>
+<td><p>00:27.864</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:28.661</p></td>
+<td><p>00:27.433</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 7838d2d403..1239ba585d 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -624,7 +624,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipea86d14c-92aa-44ff-b9e9-88d6eae93f8e 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.zipa2ab9eb9-ad64-4742-95fb-8a6404a16976 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 1b32dd68c1..6a0d70b386 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:55.266</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:53.389</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:51.370</p></td>
+<td><p>00:49.685</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>00:02.787</p></td>
+<td><p>00:02.655</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>00:01.103</p></td>
+<td><p>00:01.041</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 06f14e2c1b..864243d267 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -531,10 +531,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 22811us [22811us] (48.95%; 48.95%)
-FoldScaleAxis: 23789us [7us] (51.05%; 51.05%)
- FoldConstant: 23781us [1740us] (51.03%; 99.97%)
- InferType: 22041us [22041us] (47.30%; 92.68%)
+InferType: 22481us [22481us] (48.76%; 48.76%)
+FoldScaleAxis: 23626us [6us] (51.24%; 51.24%)
+ FoldConstant: 23619us [1689us] (51.23%; 99.97%)
+ InferType: 21930us [21930us] (47.56%; 92.85%)
</pre></div>
</div>
</div>
@@ -556,10 +556,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 24287us [24287us] (49.83%; 49.83%)
-FoldScaleAxis: 24455us [7us] (50.17%; 50.17%)
- FoldConstant: 24448us [2124us] (50.16%; 99.97%)
- InferType: 22324us [22324us] (45.80%; 91.31%)
+InferType: 21839us [21839us] (47.73%; 47.73%)
+FoldScaleAxis: 23918us [5us] (52.27%; 52.27%)
+ FoldConstant: 23914us [1681us] (52.26%; 99.98%)
+ InferType: 22233us [22233us] (48.59%; 92.97%)
</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 acc53a8a37..53d14e0058 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -580,7 +580,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 38.695518 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 53.501697 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 7c63969bc6..f2e43a739d 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -862,7 +862,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.220621 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.235994 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 aac581f704..799f6d42c8 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -477,8 +477,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018600
-Baseline: 3.413767
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017715
+Baseline: 3.290472
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -537,7 +537,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.306455
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.308936
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.337015
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.335496
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -649,7 +649,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117997
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.113693
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -726,7 +726,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110633
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109619
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -804,7 +804,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111351
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111150
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -884,7 +884,7 @@ class Module:
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147289
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146615
</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 07e9408ae8..9035feec23 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.535</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.126</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.574</p></td>
+<td><p>00:32.049</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>00:01.893</p></td>
+<td><p>00:01.852</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>00:01.068</p></td>
+<td><p>00:01.226</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 6289f8ba10..5a4762c3a7 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:23.015</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>10:04.077</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -354,27 +354,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>06:25.382</p></td>
+<td><p>06:12.159</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:44.112</p></td>
+<td><p>01:41.520</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>01:11.997</p></td>
+<td><p>01:10.557</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:33.415</p></td>
+<td><p>00:32.503</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:14.366</p></td>
+<td><p>00:13.961</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:13.743</p></td>
+<td><p>00:13.377</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 2747639c84..6df9d5aeff 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
@@ -510,74 +510,199 @@ class Module:
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- blockIdx_x = T.launch_thread("blockIdx.x", 32)
- conv2d_nchw = T.allocate([8], "float32", "local")
- pad_temp_shared = T.allocate([784], "float32", "shared")
- kernel_shared = T.allocate([256], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 98)
- conv2d_nchw_1 = T.Buffer((16,), data=conv2d_nchw, scope="local", align=16)
+ blockIdx_x = T.launch_thread("blockIdx.x", 16)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([2016], "float32", "shared")
+ kernel_shared = T.allocate([3072], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 112)
+ conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[5] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
conv2d_nchw_1[7] = T.float32(0)
- for rc_outer_outer, ry_outer_outer, rx_outer_outer in T.grid(32, 3, 3):
- cse_var_2: T.int32 = rc_outer_outer * 144
- cse_var_1: T.int32 = ry_outer_outer * 3
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
+ conv2d_nchw_1[13] = T.float32(0)
+ for rc_outer_outer, rx_outer_outer in T.grid(16, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 1568
+ cse_var_1: T.int32 = rc_outer_outer * 288
+ pad_temp_shared_1 = T.Buffer((2016,), data=pad_temp_shared, scope="shared")
+ with T.launch_thread("threadIdx.x", 112) as threadIdx_x_1:
+ data_1 = T.Buffer((25088,), data=data.data)
+ pad_temp_shared_1[threadIdx_x_1 * 18] = T.if_then_else(7 < threadIdx_x_1 * 18 % 63 and threadIdx_x_1 * 18 % 63 < 56 and 1 <= rx_outer_outer + threadIdx_x_1 * 4 % 7 and rx_outer_outer + threadIdx_x_1 * 4 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + threadIdx_x_1 * 18 % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 1] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 1) % 63 and (threadIdx_x_1 * 18 + 1) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 1) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 2] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 2) % 63 and (threadIdx_x_1 * 18 + 2) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 2) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 3] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 3) % 63 and (threadIdx_x_1 * 18 + 3) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 3) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 4] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 4) % 63 and (threadIdx_x_1 * 18 + 4) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 4) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 4) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 4) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 5] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 5) % 63 and (threadIdx_x_1 * 18 + 5) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 5) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 5) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 5) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 6] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 6) % 63 and (threadIdx_x_1 * 18 + 6) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 6) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 6) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 6) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 7] = T.if_then_else(1 <= (threadIdx_x_1 * 18 // 7 + 1) % 9 and (threadIdx_x_1 * 18 + 7) % 63 < 56 and 1 <= rx_outer_outer + threadIdx_x_1 * 4 % 7 and rx_outer_outer + threadIdx_x_1 * 4 % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 7) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 8] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 8) % 63 and (threadIdx_x_1 * 18 + 8) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 < 8, data_1[cse_var_2 + threadIdx_x_1 * 2 // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 8) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 9] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 9) % 63 and (threadIdx_x_1 * 18 + 9) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 9) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 10] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 10) % 63 and (threadIdx_x_1 * 18 + 10) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 10) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 11] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 11) % 63 and (threadIdx_x_1 * 18 + 11) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 4) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 4) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 11) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 12] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 12) % 63 and (threadIdx_x_1 * 18 + 12) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 5) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 5) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 12) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 13] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 13) % 63 and (threadIdx_x_1 * 18 + 13) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 6) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 6) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 13) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 14] = T.if_then_else(1 <= (threadIdx_x_1 * 18 // 7 + 2) % 9 and (threadIdx_x_1 * 18 + 14) % 63 < 56 and 1 <= rx_outer_outer + threadIdx_x_1 * 4 % 7 and rx_outer_outer + threadIdx_x_1 * 4 % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 14) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 15] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 15) % 63 and (threadIdx_x_1 * 18 + 15) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 1) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 15) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 16] = T.if_then_else(7 <= (threadIdx_x_1 * 18 + 16) % 63 and (threadIdx_x_1 * 18 + 16) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 2) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 16) % 63 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 18 + 17] = T.if_then_else(7 < (threadIdx_x_1 * 18 + 17) % 63 and (threadIdx_x_1 * 18 + 17) % 63 < 56 and 1 <= rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 and rx_outer_outer + (threadIdx_x_1 * 4 + 3) % 7 < 8, data_1[cse_var_2 + (threadIdx_x_1 * 2 + 1) // 7 * 49 + rx_outer_outer + (threadIdx_x_1 * 18 + 17) % 63 - 8], T.float32(0))
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((784,), data=pad_temp_shared, scope="shared")
- data_1 = T.Buffer((25088,), data=data.data)
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 98] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 90], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 196] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 188], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 294] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 286], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 392] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 384], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 490] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 482], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 588] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 580], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 98):
- pad_temp_shared_1[threadIdx_x_1 + 686] = T.if_then_else(1 <= threadIdx_x_1 % 49 // 7 + ry_outer_outer and threadIdx_x_1 % 49 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 784 + ry_outer_outer * 7 + threadIdx_x_1 + rx_outer_outer + 678], T.float32(0))
- threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((256,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((3072,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 16 * 4608 + cse_var_2 + threadIdx_x_2 % 16 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 98):
- kernel_shared_1[threadIdx_x_2 + 98] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 98) // 16 * 4608 + cse_var_2 + (threadIdx_x_2 + 2) % 16 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_2, 98):
- if T.likely(threadIdx_x_2 < 60):
- kernel_shared_1[threadIdx_x_2 + 196] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 196) // 16 * 4608 + cse_var_2 + (threadIdx_x_2 + 4) % 16 * 9 + cse_var_1 + rx_outer_outer]
- for rc_outer_inner in range(8):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 128]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 16]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 144]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 1]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 129]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 17]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 145]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 32]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 160]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 48]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 176]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 33]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 161]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 49]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 98 + threadIdx_x % 49 + 49] * kernel_shared_1[threadIdx_x // 49 * 64 + rc_outer_inner * 2 + 177]
- for i1_inner in range(4):
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 112) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 112) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 224) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 224) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 336) // 96 * 96 + (threadIdx_x_1 // 3 + 16) % 32 * 3 + threadIdx_x_1 % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 336) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 // 3 + 16) % 32 * 9 + threadIdx_x_1 % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 448) // 96 * 96 + (threadIdx_x_1 + 64) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 448) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 64) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 560) // 96 * 96 + (threadIdx_x_1 + 80) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 560) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 80) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1 + 672] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer + 32256]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 784) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 784) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 896) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 896) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1008) // 96 * 96 + (threadIdx_x_1 // 3 + 16) % 32 * 3 + threadIdx_x_1 % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1008) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 // 3 + 16) % 32 * 9 + threadIdx_x_1 % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1120) // 96 * 96 + (threadIdx_x_1 + 64) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1120) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 64) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1232) // 96 * 96 + (threadIdx_x_1 + 80) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1232) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 80) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1 + 1344] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer + 64512]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1456) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1456) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1568) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1568) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1680) // 96 * 96 + (threadIdx_x_1 // 3 + 16) % 32 * 3 + threadIdx_x_1 % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1680) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 // 3 + 16) % 32 * 9 + threadIdx_x_1 % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1792) // 96 * 96 + (threadIdx_x_1 + 64) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1792) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 64) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 1904) // 96 * 96 + (threadIdx_x_1 + 80) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 1904) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 80) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1 + 2016] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer + 96768]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2128) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2128) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2240) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2240) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2352) // 96 * 96 + (threadIdx_x_1 // 3 + 16) % 32 * 3 + threadIdx_x_1 % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2352) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 // 3 + 16) % 32 * 9 + threadIdx_x_1 % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2464) // 96 * 96 + (threadIdx_x_1 + 64) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2464) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 64) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2576) // 96 * 96 + (threadIdx_x_1 + 80) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2576) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 80) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[threadIdx_x_1 + 2688] = kernel_1[blockIdx_x * 147456 + threadIdx_x_1 // 96 * 4608 + cse_var_1 + threadIdx_x_1 % 96 * 3 + rx_outer_outer + 129024]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2800) // 96 * 96 + (threadIdx_x_1 + 16) % 96 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2800) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 16) % 96 // 3 * 9 + (threadIdx_x_1 + 1) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ kernel_shared_1[(threadIdx_x_1 + 2912) // 96 * 96 + (threadIdx_x_1 + 32) % 96 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 2912) // 96 * 4608 + cse_var_1 + (threadIdx_x_1 + 32) % 96 // 3 * 9 + (threadIdx_x_1 + 2) % 3 * 3 + rx_outer_outer]
+ with T.launch_thread(threadIdx_x_1, 112):
+ if T.likely(threadIdx_x_1 < 48):
+ kernel_shared_1[(threadIdx_x_1 + 3024) // 96 * 96 + threadIdx_x_1 + 48] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_1 + 3024) // 96 * 4608 + cse_var_1 + threadIdx_x_1 * 3 + rx_outer_outer + 144]
+ for rc_outer_inner in range(16):
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 3]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 96]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 99]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 4]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 97]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 70] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 100]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 5]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 14] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 21] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 35] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 42] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 49] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 98]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 77] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 84] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 98] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 105] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 112] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 126 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 6 + 101]
+ for i1_inner, i2_inner in T.grid(2, 7):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 196 + i1_inner * 49 + threadIdx_x % 49] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 4 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 784 + threadIdx_x // 49 * 196 + i1_inner * 49 + threadIdx_x % 49 + 392] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 16 + threadIdx_x // 49 * 4 + i1_inner + 8], T.float32(0))
+ compute_1[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i1_inner * 7 + i2_inner] + bias_1[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -611,7 +736,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.259 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.271 ms
</pre></div>
</div>
</div>
@@ -640,33 +765,33 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
-conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -689,14 +814,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=18)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -714,60 +839,168 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[784];
- __shared__ float kernel_shared[256];
+extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[2016];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 90)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 188)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 286)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 482)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 580)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((1 <= (((((int)threadIdx.x) % 49) / 7) + ry_outer_outer)) && ((((((int)threadIdx.x) % 49) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 784) + (ry_outer_outer * 7)) + ((int)threadIdx.x)) + rx_outer_outer) + 678)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) >> 4) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 2) & 15) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 60) {
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) >> 4) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 4) & 15) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 128)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 144)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 145)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 160)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 98) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 176)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 161)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 49)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 98) + (((int)threadIdx.x) % 49)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 49) * 64) + (rc_outer_inner * 2)) + 177)]));
- }
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 18)] = (((((7 < ((((int)threadIdx.x) * 18) % 63)) && (((((int)threadIdx.x) * 18) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + ((((int)threadIdx.x) * 18) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 1)] = (((((7 < (((((int)threadIdx.x) * 18) + 1) % 63)) && ((((((int)threadIdx.x) * 18) + 1) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 1) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 2)] = (((((7 < (((((int)threadIdx.x) * 18) + 2) % 63)) && ((((((int)threadIdx.x) * 18) + 2) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 2) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 3)] = (((((7 < (((((int)threadIdx.x) * 18) + 3) % 63)) && ((((((int)threadIdx.x) * 18) + 3) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 3) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 4)] = (((((7 < (((((int)threadIdx.x) * 18) + 4) % 63)) && ((((((int)threadIdx.x) * 18) + 4) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 4) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 5)] = (((((7 < (((((int)threadIdx.x) * 18) + 5) % 63)) && ((((((int)threadIdx.x) * 18) + 5) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 5) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 5) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 5) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 6)] = (((((7 < (((((int)threadIdx.x) * 18) + 6) % 63)) && ((((((int)threadIdx.x) * 18) + 6) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 6) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 6) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 6) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 7)] = (((((1 <= ((((((int)threadIdx.x) * 18) / 7) + 1) % 9)) && ((((((int)threadIdx.x) * 18) + 7) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 7) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 8)] = (((((7 < (((((int)threadIdx.x) * 18) + 8) % 63)) && ((((((int)threadIdx.x) * 18) + 8) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 8) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 9)] = (((((7 < (((((int)threadIdx.x) * 18) + 9) % 63)) && ((((((int)threadIdx.x) * 18) + 9) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 9) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 10)] = (((((7 < (((((int)threadIdx.x) * 18) + 10) % 63)) && ((((((int)threadIdx.x) * 18) + 10) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 10) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 11)] = (((((7 < (((((int)threadIdx.x) * 18) + 11) % 63)) && ((((((int)threadIdx.x) * 18) + 11) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 4) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 11) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 12)] = (((((7 < (((((int)threadIdx.x) * 18) + 12) % 63)) && ((((((int)threadIdx.x) * 18) + 12) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 5) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 5) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 12) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 13)] = (((((7 < (((((int)threadIdx.x) * 18) + 13) % 63)) && ((((((int)threadIdx.x) * 18) + 13) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 6) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 6) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 13) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 14)] = (((((1 <= ((((((int)threadIdx.x) * 18) / 7) + 2) % 9)) && ((((((int)threadIdx.x) * 18) + 14) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 14) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 15)] = (((((7 < (((((int)threadIdx.x) * 18) + 15) % 63)) && ((((((int)threadIdx.x) * 18) + 15) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 15) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 16)] = (((((7 <= (((((int)threadIdx.x) * 18) + 16) % 63)) && ((((((int)threadIdx.x) * 18) + 16) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 16) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 18) + 17)] = (((((7 < (((((int)threadIdx.x) * 18) + 17) % 63)) && ((((((int)threadIdx.x) * 18) + 17) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 7) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 18) + 17) % 63)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 112) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 224) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 336) / 96) * 96) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 96) * 96) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 560) / 96) * 96) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((((((int)threadIdx.x) + 784) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 896) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1008) / 96) * 96) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1120) / 96) * 96) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1232) / 96) * 96) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 64512)];
+ kernel_shared[(((((((int)threadIdx.x) + 1456) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1568) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1680) / 96) * 96) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1792) / 96) * 96) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 1904) / 96) * 96) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 96768)];
+ kernel_shared[(((((((int)threadIdx.x) + 2128) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2240) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2352) / 96) * 96) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2464) / 96) * 96) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2576) / 96) * 96) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) % 96) * 3)) + rx_outer_outer) + 129024)];
+ kernel_shared[(((((((int)threadIdx.x) + 2800) / 96) * 96) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((((((int)threadIdx.x) + 2912) / 96) * 96) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 48) {
+ kernel_shared[(((((((int)threadIdx.x) + 3024) / 96) * 96) + ((int)threadIdx.x)) + 48)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 144)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 16; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 126) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 126) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 97)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 49)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 98)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 112)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 126) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 6)) + 101)]));
}
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 8)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -802,7 +1035,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 25.382 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 12.159 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 89a88cd181..37e9b4edb5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -921,7 +921,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.1330 8.1306 8.1398 8.1287 0.0049
+ 8.0998 8.0989 8.1043 8.0962 0.0034
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.997 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.557 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 1f06a476a8..31291e41fe 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -940,7 +940,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 760.4988 760.7738 763.0901 757.6325 2.2365
+ 742.0950 742.4272 742.7905 741.0674 0.7416
</pre></div>
</div>
</div>
@@ -962,7 +962,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 44.112 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.520 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 d63c5a2195..79a735a23a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -637,26 +637,26 @@ class Module:
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.Buffer((1024,), data=compute_1)
- for i_inner_init, j_init in T.grid(64, 16):
- compute_2[i_inner_init * 16 + j_init] = T.float32(0)
- for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 32}), 64, 16):
- cse_var_1 = T.int32()
- placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
- cse_var_2: T.int32 = i0_outer_i1_outer_fused % 32
- if T.likely(elem_idx < placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]):
+ for i0_outer_i1_outer_fused in T.parallel(1024):
+ compute_1 = T.allocate([64], "float32", "global")
+ compute_2 = T.Buffer((64,), data=compute_1)
+ for nb_j_inner in range(2):
+ for i_inner_init, j_init in T.grid(2, 16):
+ compute_2[i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 2, 16):
+ cse_var_1 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_inner * 32 + nb_j_inner * 16 + j
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- cse_var_3: T.int32 = i_inner * 16 + j
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_2] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_2] + elem_idx]], T.float32(0))
- for i0_inner in range(64):
- cse_var_4: T.int32 = i0_outer_i1_outer_fused // 32 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 512 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner in range(2):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 1024 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_4:cse_var_4 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_4:cse_var_4 + 16], T.Broadcast(T.float32(0), 16))
+ compute_3[cse_var_4:cse_var_4 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_4:cse_var_4 + 32], T.Broadcast(T.float32(0), 32))
</pre></div>
</div>
</div>
@@ -690,7 +690,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.797 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.879 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 f2246adbca..00d7153600 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:56.140</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:56.794</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,7 +354,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:56.105</p></td>
+<td><p>00:56.760</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index d6aa92f271..435afc8608 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -695,7 +695,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4038283
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2316543
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -818,9 +818,28 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6833871
-No: 3 GFLOPS: 12.77/12.77 result: MeasureResult(costs=(0.0181309445,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6604640483856201, timestamp=1680264160.6413214) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6797780
-No: 4 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
+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, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1772544
+No: 3 GFLOPS: 242.17/242.17 result: MeasureResult(costs=(0.0009559260745341616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4570045471191406, timestamp=1680316947.9738998) [('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7012841
+No: 4 GFLOPS: 160.47/242.17 result: MeasureResult(costs=(0.0014426688571428572,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0958614349365234, timestamp=1680316950.4147267) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8870647
+No: 5 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3807167
+No: 6 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -942,8 +961,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4629381
-No: 5 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2560072
+No: 7 GFLOPS: 143.47/242.17 result: MeasureResult(costs=(0.0016135418309859155,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0929834842681885, timestamp=1680316962.9643157) [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 7, 1, 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', 512), ('unroll_explicit', 1)],None,7174023
+No: 8 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1065,929 +1085,11 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 256, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5062473
-No: 6 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 399, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 179, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007fba0c91bfa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:187
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
-Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,237442
-No: 7 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6735081
-No: 8 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9024820
-No: 9 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10342907
-No: 10 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3760478
-No: 11 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
- func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
- func = build(s, args, target=target, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, 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:1734
- 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:1674
- 19: run<>
- at ../include/tvm/runtime/packed_func.h:1634
- 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1634
- 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
- at ../include/tvm/runtime/packed_func.h:1649
- 13: operator()
- at ../src/driver/driver_api.cc:402
- 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:388
- 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
- at ../src/driver/driver_api.cc:283
- 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:451
- 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:1753
- 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:1697
- 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:1621
- 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 875, in verify_pass
- raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10288904
-No: 12 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 399, in evaluator
- blob = feval(*args)
- File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
- File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
- at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 179, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007f89cd349fa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:187
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
- at ../include/tvm/runtime/packed_func.h:1621
- 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/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
-
-Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2225951
-No: 13 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2972689
+No: 9 GFLOPS: 61.98/242.17 result: MeasureResult(costs=(0.00373492735,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7704739570617676, timestamp=1680316967.8509436) [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6267951
+No: 10 GFLOPS: 157.19/242.17 result: MeasureResult(costs=(0.0014727039857142857,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.386355876922607, timestamp=1680316968.709615) [('tile_f', [-1, 1, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8814443
+No: 11 GFLOPS: 19.96/242.17 result: MeasureResult(costs=(0.011595925222222222,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.137821912765503, timestamp=1680316969.6179323) [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3687793
+No: 12 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2109,8 +1211,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,84242
-No: 14 GFLOPS: 0.00/12.77 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,378493
+No: 13 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2232,9 +1334,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,47837
-No: 15 GFLOPS: 18.97/18.97 result: MeasureResult(costs=(0.012202183111111112,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7925684452056885, timestamp=1680264187.0836403) [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3405610
-No: 16 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6133572
+No: 14 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2356,8 +1457,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 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,653557
-No: 17 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,149371
+No: 15 GFLOPS: 2.71/242.17 result: MeasureResult(costs=(0.08546508775,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.6383960247039795, timestamp=1680316974.4706283) [('tile_f', [-1, 4, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3874167
+No: 16 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2479,8 +1581,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5064228
-No: 18 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+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, 7, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6063187
+No: 17 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2602,8 +1704,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('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,9201362
-No: 19 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2161915
+No: 18 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2725,8 +1827,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10398817
-No: 20 GFLOPS: 0.00/18.97 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6218501
+No: 19 GFLOPS: 0.00/242.17 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2848,7 +1950,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2342024
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9929413
+No: 20 GFLOPS: 6.85/242.17 result: MeasureResult(costs=(0.033783313749999995,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.29587197303772, timestamp=1680316982.025626) [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5101067
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2887,9 +1990,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3405610
+[('tile_f', [-1, 1, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7012841
Finish loading 20 records
-Time cost of this operator: 0.012520
+Time cost of this operator: 0.001341
</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 558a93c5e3..5703ec85b0 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -649,10 +649,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.1 98.75 (1, 2, 10, 10, 3) 2 1 [316.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.04 0.95 (1, 6, 10, 10) 1 1 [3.04]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.301 (1, 1, 10, 10, 3) 1 1 [0.962]
-Total_time - 320.102 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 318.1 98.744 (1, 2, 10, 10, 3) 2 1 [318.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.082 0.957 (1, 6, 10, 10) 1 1 [3.082]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.299 (1, 1, 10, 10, 3) 1 1 [0.963]
+Total_time - 322.145 - - - - -
</pre></div>
</div>
</div>
@@ -704,13 +704,13 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.6 97.501 (1, 6, 10, 10, 1) 2 1 [103.6]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.797 1.691 (1, 6, 10, 10) 1 1 [1.797]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.858 0.807 (1, 3, 10, 10, 1) 1 1 [0.858]
-Total_time - 106.255 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 103.3 97.483 (1, 6, 10, 10, 1) 2 1 [103.3]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.805 1.703 (1, 6, 10, 10) 1 1 [1.805]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.862 0.814 (1, 3, 10, 10, 1) 1 1 [0.862]
+Total_time - 105.967 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.086 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.858 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/9ccca8fd489a1486ac71b55a55c320c5/micro_autotune.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_autotune.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 5084735a20..c833ea725d 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -460,8 +460,8 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
- 61%|###### | 2.09M/3.42M [00:00<00:00, 10.1MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 16.1MB/s]
+ 61%|###### | 2.09M/3.42M [00:00<00:00, 20.0MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 30.6MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -587,7 +587,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.317 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.127 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 75591441e8..f763396360 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -528,7 +528,7 @@ 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/tmp8juwrav6/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmphyq_bic6/images/random'
</pre></div>
</div>
</div>
@@ -588,8 +588,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp8juwrav6/images/target contains 8144 images
-/tmp/tmp8juwrav6/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], [0.0, 1.0], [0.0, 1.0], [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/tmphyq_bic6/images/target contains 8144 images
+/tmp/tmphyq_bic6/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -701,13 +701,13 @@ 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 - 41s - loss: 0.2104 - accuracy: 0.9288 - val_loss: 0.1292 - val_accuracy: 0.9558 - 41s/epoch - 124ms/step
+328/328 - 41s - loss: 0.2032 - accuracy: 0.9299 - val_loss: 0.2038 - val_accuracy: 0.9332 - 41s/epoch - 125ms/step
Epoch 2/3
-328/328 - 35s - loss: 0.0861 - accuracy: 0.9693 - val_loss: 0.1373 - val_accuracy: 0.9524 - 35s/epoch - 106ms/step
+328/328 - 34s - loss: 0.0977 - accuracy: 0.9626 - val_loss: 0.0982 - val_accuracy: 0.9660 - 34s/epoch - 105ms/step
Epoch 3/3
-328/328 - 35s - loss: 0.0574 - accuracy: 0.9792 - val_loss: 0.1309 - val_accuracy: 0.9566 - 35s/epoch - 105ms/step
+328/328 - 34s - loss: 0.0661 - accuracy: 0.9748 - val_loss: 0.0865 - val_accuracy: 0.9709 - 34s/epoch - 104ms/step
-<keras.callbacks.History object at 0x7fa5e3345a90>
+<keras.callbacks.History object at 0x7fa7e9342cd0>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 33.391 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 22.010 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 4ed0b09224..5661d7dfa9 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:42.021</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:24.587</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,27 +354,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">5. Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:33.391</p></td>
+<td><p>04:22.010</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:23.086</p></td>
+<td><p>01:19.858</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:19.317</p></td>
+<td><p>01:17.127</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">3. microTVM Ahead-of-Time (AOT) Compilation</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:10.515</p></td>
+<td><p>00:10.266</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_custom_ide.html#sphx-glr-how-to-work-with-microtvm-micro-custom-ide-py"><span class="std std-ref">9. Bring microTVM to your own development environment</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_custom_ide.py</span></code>)</p></td>
-<td><p>00:08.050</p></td>
+<td><p>00:07.882</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:07.661</p></td>
+<td><p>00:07.444</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">7. Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 0a209b10eb..2da6f6921a 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:37.417</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:36.366</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,19 +354,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.684</p></td>
+<td><p>00:31.847</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>00:02.910</p></td>
+<td><p>00:02.848</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>00:01.817</p></td>
+<td><p>00:01.665</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 20ad1e633a..8ba189e37b 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -540,7 +540,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fa37b7170e0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fa43a61b0e0>
</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 f671c860d2..7bd4c4513a 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:09.451</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.712</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,31 +354,31 @@
</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>00:06.477</p></td>
+<td><p>00:05.950</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>00:01.447</p></td>
+<td><p>00:01.275</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>00:00.637</p></td>
+<td><p>00:00.612</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>00:00.611</p></td>
+<td><p>00:00.599</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>00:00.129</p></td>
+<td><p>00:00.128</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.064</p></td>
+<td><p>00:00.063</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.055</p></td>
+<td><p>00:00.054</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index e834856b0c..6a2d26b007 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1621,7 +1621,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1905,7 +1905,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 71d0772eaf..c3adedc979 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/b724c87f7/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 30237709a2..af9aec5074 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/b724c87f7/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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 28fdf6842d..84ad069448 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/b724c87f7/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L357">runtime.ts:357</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L376">runtime.ts:376</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L367">runtime.ts:367</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index a5d65c8558..58eadc49f0 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/b724c87f7/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L299">runtime.ts:299</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L320">runtime.ts:320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L327">runtime.ts:327</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index 69747eb3cc..b4ff4a246a 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/b724c87f7/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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 63f84ae0dd..5d693bde35 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/b724c87f7/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L50">runtime.ts:50</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L48">runtime.ts:48</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L77">runtime.ts:77</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L67">runtime.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L85">runtime.ts:85</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L96">runtime.ts:96</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L73">runtime.ts:73</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 2fec4befa9..d6225c05ae 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -161,7 +161,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L844">runtime.ts:844</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L834">runtime.ts:834</a></li>
</ul>
</aside>
</section>
@@ -234,7 +234,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L833">runtime.ts:833</a></li>
</ul>
</aside>
</section>
@@ -251,7 +251,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L973">runtime.ts:973</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -296,7 +296,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -318,7 +318,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L901">runtime.ts:901</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -381,7 +381,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -412,7 +412,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -453,7 +453,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -491,7 +491,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L922">runtime.ts:922</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -508,7 +508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -552,7 +552,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L943">runtime.ts:943</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -577,7 +577,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -609,7 +609,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -640,7 +640,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -672,7 +672,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -695,7 +695,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -729,7 +729,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L986">runtime.ts:986</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -769,7 +769,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -817,7 +817,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -857,7 +857,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -900,7 +900,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -938,7 +938,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1014,7 +1014,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1046,7 +1046,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1078,7 +1078,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1110,7 +1110,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1141,7 +1141,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L957">runtime.ts:957</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index d17ccfd740..67e5128417 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/b724c87f7/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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 1e93b05344..32798a7713 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L614">runtime.ts:614</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L626">runtime.ts:626</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -186,7 +186,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L653">runtime.ts:653</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L641">runtime.ts:641</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L687">runtime.ts:687</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index dde245e451..80ee5460f4 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/b724c87f7/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L401">runtime.ts:401</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L394">runtime.ts:394</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L390">runtime.ts:390</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L388">runtime.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L392">runtime.ts:392</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -225,7 +225,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L480">runtime.ts:480</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -258,7 +258,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L524">runtime.ts:524</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -290,7 +290,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L465">runtime.ts:465</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -307,7 +307,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L458">runtime.ts:458</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -339,7 +339,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L584">runtime.ts:584</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -363,7 +363,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L553">runtime.ts:553</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index b7af5b46ad..1e13d80859 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -117,7 +117,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L255">runtime.ts:255</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -163,7 +163,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L264">runtime.ts:264</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index a8ab16f5a5..69355f42df 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/b724c87f7/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/runtimecontext.html b/docs/reference/api/typedoc/classes/runtimecontext.html
index 2ed61b7874..c6dd891071 100644
--- a/docs/reference/api/typedoc/classes/runtimecontext.html
+++ b/docs/reference/api/typedoc/classes/runtimecontext.html
@@ -132,7 +132,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L148">runtime.ts:148</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Item<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
</section>
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Size<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L144">runtime.ts:144</a></li>
</ul>
</aside>
</section>
@@ -192,7 +192,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Make<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
</section>
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Sys<wbr>Lib<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L146">runtime.ts:146</a></li>
</ul>
</aside>
</section>
@@ -219,7 +219,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -263,7 +263,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L163">runtime.ts:163</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -280,7 +280,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L208">runtime.ts:208</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
@@ -309,7 +309,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -326,7 +326,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L167">runtime.ts:167</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -343,7 +343,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 3d052a55ba..dcd44b7eea 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/b724c87f7/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L233">runtime.ts:233</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmarray.html b/docs/reference/api/typedoc/classes/tvmarray.html
index 3a34a9d878..f69269f64b 100644
--- a/docs/reference/api/typedoc/classes/tvmarray.html
+++ b/docs/reference/api/typedoc/classes/tvmarray.html
@@ -133,7 +133,7 @@
<aside class="tsd-sources">
<p>Overrides <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#constructor">constructor</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L784">runtime.ts:784</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -162,7 +162,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#ctx">ctx</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#dispose">dispose</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -197,7 +197,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L804">runtime.ts:804</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -230,7 +230,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#gethandle">getHandle</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L796">runtime.ts:796</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -283,7 +283,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typeindex">typeIndex</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -306,7 +306,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typekey">typeKey</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmobject.html b/docs/reference/api/typedoc/classes/tvmobject.html
index 06c22c879b..2affd98a53 100644
--- a/docs/reference/api/typedoc/classes/tvmobject.html
+++ b/docs/reference/api/typedoc/classes/tvmobject.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">ctx<span class="tsd-signature-symbol">:</span> <a href="runtimecontext.html" class="tsd-signature-type">RuntimeContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -175,7 +175,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -192,7 +192,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -246,7 +246,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index a57a3475ae..3a47d3849c 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/b724c87f7/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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 b1f8450a65..f17d6f4deb 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/b724c87f7/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index dd2466e230..c6ce6cdee1 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/b724c87f7/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L812">runtime.ts:812</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L811">runtime.ts:811</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 1c4e99983c..9154b97143 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/b724c87f7/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L339">runtime.ts:339</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L337">runtime.ts:337</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L340">runtime.ts:340</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L338">runtime.ts:338</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 8f9dee9381..a89d825e46 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/b724c87f7/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 079030e979..33c75d0e78 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/b724c87f7/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 91df65d77b..a950304cc7 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">FObject<wbr>Constructor<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, lib<span class="tsd-signature-symbol">: </span><a href="classes/ffilibrary.html" class="tsd-signature-type">FFILibrary</a>, ctx<span class="tsd-signature-symbol">: </span><a href="classes/runtimecontext.html" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L778">runtime.ts:778</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -288,7 +288,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -376,7 +376,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -420,7 +420,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -456,7 +456,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -508,7 +508,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -556,7 +556,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -595,7 +595,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -651,7 +651,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -687,7 +687,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -726,7 +726,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -765,7 +765,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -808,7 +808,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -838,7 +838,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -874,7 +874,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -922,7 +922,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -962,7 +962,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -998,7 +998,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Get<wbr>Type<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1037,7 +1037,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Index2<wbr>Key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_index<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, out_type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1076,7 +1076,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Key2<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1115,7 +1115,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1157,7 +1157,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1193,7 +1193,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1229,7 +1229,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1269,7 +1269,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1321,7 +1321,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1357,7 +1357,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1372,7 +1372,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L37">runtime.ts:37</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L37">runtime.ts:37</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1387,7 +1387,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1402,7 +1402,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1417,7 +1417,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Base<span class="tsd-signature-symbol">:</span> <a href="classes/tvmobject.html" class="tsd-signature-type">TVMObject</a><span class="tsd-signature-symbol"> | </span><a href="classes/ndarray.html" class="tsd-signature-type">NDArray</a><span class="tsd-signature-symbol"> | </span><a href="classes/module.html" class="tsd-signature-type">Module</a><span class="tsd-signature-symbol"> | </span><a href="index.html#packedfunc" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L781">runtime.ts:781</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L781">runtime.ts:781</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1435,7 +1435,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1457,7 +1457,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1489,7 +1489,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1518,7 +1518,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1555,7 +1555,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1586,7 +1586,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1608,7 +1608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1639,7 +1639,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1661,7 +1661,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1726,7 +1726,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1748,7 +1748,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L343">runtime.ts:343</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L343">runtime.ts:343</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1757,7 +1757,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L344">runtime.ts:344</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L344">runtime.ts:344</a></li>
</ul>
</aside>
</section>
@@ -1767,7 +1767,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L345">runtime.ts:345</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L345">runtime.ts:345</a></li>
</ul>
</aside>
</section>
@@ -1777,7 +1777,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L346">runtime.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L346">runtime.ts:346</a></li>
</ul>
</aside>
</section>
@@ -1787,7 +1787,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L347">runtime.ts:347</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L347">runtime.ts:347</a></li>
</ul>
</aside>
</section>
@@ -1798,7 +1798,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L272">runtime.ts:272</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L272">runtime.ts:272</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1807,7 +1807,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L273">runtime.ts:273</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L273">runtime.ts:273</a></li>
</ul>
</aside>
</section>
@@ -1817,7 +1817,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L277">runtime.ts:277</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L277">runtime.ts:277</a></li>
</ul>
</aside>
</section>
@@ -1827,7 +1827,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L274">runtime.ts:274</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L274">runtime.ts:274</a></li>
</ul>
</aside>
</section>
@@ -1837,7 +1837,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L275">runtime.ts:275</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L275">runtime.ts:275</a></li>
</ul>
</aside>
</section>
@@ -1847,7 +1847,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L276">runtime.ts:276</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L276">runtime.ts:276</a></li>
</ul>
</aside>
</section>
@@ -1858,7 +1858,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L280">runtime.ts:280</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L280">runtime.ts:280</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1867,7 +1867,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L283">runtime.ts:283</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L283">runtime.ts:283</a></li>
</ul>
</aside>
</section>
@@ -1877,7 +1877,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L281">runtime.ts:281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L281">runtime.ts:281</a></li>
</ul>
</aside>
</section>
@@ -1887,7 +1887,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L282">runtime.ts:282</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L282">runtime.ts:282</a></li>
</ul>
</aside>
</section>
@@ -1897,7 +1897,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L286">runtime.ts:286</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L286">runtime.ts:286</a></li>
</ul>
</aside>
</section>
@@ -1907,7 +1907,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L284">runtime.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L284">runtime.ts:284</a></li>
</ul>
</aside>
</section>
@@ -1917,7 +1917,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L285">runtime.ts:285</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L285">runtime.ts:285</a></li>
</ul>
</aside>
</section>
@@ -1927,7 +1927,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/runtime.ts#L287">runtime.ts:287</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/web/src/runtime.ts#L287">runtime.ts:287</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 2b16076b6b..89de6221e4 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/b724c87f7/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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 ad3d21db0a..475da47cf2 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/b724c87f7/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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 f14794ad82..909a1d6fca 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/b724c87f7/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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/b724c87f7/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/98007f90d/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 56e09441e8..d75d558584 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 b2ef488976..4e762cd77b 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:31.522</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:30.556</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:31.516</p></td>
+<td><p>00:30.550</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index a60c9c0ac4..7966e7fcd8 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -588,7 +588,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 33.62s!
+resnet18_v1 inference graph built in 32.56s!
</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 026ebc4f48..bacf8ec8b2 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -606,7 +606,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 22.98s!
+yolov3-tiny inference graph built in 22.28s!
</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 f70a7a2613..eb71735704 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:40.749</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:38.779</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -353,12 +353,12 @@
<col style="width: 7%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:50.469</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
+<td><p>00:49.436</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:50.279</p></td>
+<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>00:49.343</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 9b75da0ca6..2a50f43519 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.188</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.174</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.703</p></td>
+<td><p>00:02.707</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>00:00.484</p></td>
+<td><p>00:00.468</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 5d7205fdf9..e50baef492 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.825</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.799</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.426</p></td>
+<td><p>00:00.412</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>00:00.399</p></td>
+<td><p>00:00.387</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 d23b9edf66..dbb112188f 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -497,6 +497,9 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
+</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>
@@ -574,7 +577,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.841 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.480 ms
</pre></div>
</div>
</div>
@@ -646,7 +649,7 @@ 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 35.957 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.657 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 1adfa0c190..f4eaa8f491 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -685,16 +685,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 12.58/12.58 result: MeasureResult(costs=(0.0213354186,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6930179595947266, timestamp=1680262472.2431269) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
-No: 2 GFLOPS: 1.53/12.58 result: MeasureResult(costs=(0.17585374380000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0729477405548096, timestamp=1680262475.3201342) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
-No: 3 GFLOPS: 11.77/12.58 result: MeasureResult(costs=(0.0228077934,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7097334861755371, timestamp=1680262477.2220645) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 0.51/12.58 result: MeasureResult(costs=(0.5274926004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.664091348648071, timestamp=1680262487.1920028) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
-No: 5 GFLOPS: 3.32/12.58 result: MeasureResult(costs=(0.0808814766,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5575499534606934, timestamp=1680262490.4692483) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
-No: 6 GFLOPS: 4.37/12.58 result: MeasureResult(costs=(0.0614117778,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2563884258270264, timestamp=1680262491.711772) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
-No: 7 GFLOPS: 14.56/14.56 result: MeasureResult(costs=(0.018437087600000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9013512134552002, timestamp=1680262492.267989) [('tile_y', [-1, 64]), ('tile_x', [-1, 64])],None,66
-No: 8 GFLOPS: 12.10/14.56 result: MeasureResult(costs=(0.0221832424,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7399411201477051, timestamp=1680262492.8867397) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
-No: 9 GFLOPS: 3.13/14.56 result: MeasureResult(costs=(0.0857591424,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.582322359085083, timestamp=1680262494.5826154) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
-No: 10 GFLOPS: 1.50/14.56 result: MeasureResult(costs=(0.1792620768,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.036386251449585, timestamp=1680262497.6711853) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 1 GFLOPS: 3.07/3.07 result: MeasureResult(costs=(0.0875686056,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6519381999969482, timestamp=1680315287.6446161) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 2 GFLOPS: 10.85/10.85 result: MeasureResult(costs=(0.0247445388,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6787183284759521, timestamp=1680315289.5259745) [('tile_y', [-1, 4]), ('tile_x', [-1, 128])],None,72
+No: 3 GFLOPS: 8.94/10.85 result: MeasureResult(costs=(0.03003245,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7182004451751709, timestamp=1680315290.262789) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
+No: 4 GFLOPS: 0.51/10.85 result: MeasureResult(costs=(0.5248235898,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.634685754776001, timestamp=1680315300.141615) [('tile_y', [-1, 256]), ('tile_x', [-1, 1])],None,8
+No: 5 GFLOPS: 12.70/12.70 result: MeasureResult(costs=(0.0211389882,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6035053730010986, timestamp=1680315300.9063146) [('tile_y', [-1, 32]), ('tile_x', [-1, 128])],None,75
+No: 6 GFLOPS: 11.89/12.70 result: MeasureResult(costs=(0.0225691456,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6688330173492432, timestamp=1680315301.526111) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 7 GFLOPS: 10.27/12.70 result: MeasureResult(costs=(0.026147772200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.655611515045166, timestamp=1680315303.4412062) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
+No: 8 GFLOPS: 1.54/12.70 result: MeasureResult(costs=(0.1745465388,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.03352952003479, timestamp=1680315306.4876146) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+No: 9 GFLOPS: 0.88/12.70 result: MeasureResult(costs=(0.3044655076,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.083791017532349, timestamp=1680315311.6972497) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+No: 10 GFLOPS: 3.33/12.70 result: MeasureResult(costs=(0.080644848,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5073270797729492, timestamp=1680315313.2437055) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
</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 0adb716f91..349b3ad251 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -563,7 +563,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 512.6999624700011, 'median': 512.9441132000068, 'std': 1.2014829374162335}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 509.58684035999795, 'median': 508.9386698999931, 'std': 2.6515574204392656}
</pre></div>
</div>
</div>
@@ -715,179 +715,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 11.14/ 23.29 GFLOPS | Progress: (4/20) | 10.40 s
-[Task 1/25] Current/Best: 9.71/ 23.29 GFLOPS | Progress: (8/20) | 17.54 s
-[Task 1/25] Current/Best: 14.24/ 23.29 GFLOPS | Progress: (12/20) | 20.19 s
-[Task 1/25] Current/Best: 11.33/ 23.29 GFLOPS | Progress: (16/20) | 22.43 s
-[Task 1/25] Current/Best: 7.39/ 23.29 GFLOPS | Progress: (20/20) | 28.77 s Done.
+[Task 1/25] Current/Best: 6.37/ 22.16 GFLOPS | Progress: (4/20) | 10.83 s
+[Task 1/25] Current/Best: 7.04/ 22.16 GFLOPS | Progress: (8/20) | 15.53 s
+[Task 1/25] Current/Best: 14.25/ 24.12 GFLOPS | Progress: (12/20) | 18.02 s
+[Task 1/25] Current/Best: 11.56/ 24.12 GFLOPS | Progress: (16/20) | 20.57 s
+[Task 1/25] Current/Best: 15.09/ 24.12 GFLOPS | Progress: (20/20) | 22.73 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 17.33/ 18.41 GFLOPS | Progress: (4/20) | 4.54 s
-[Task 2/25] Current/Best: 5.08/ 22.19 GFLOPS | Progress: (8/20) | 6.60 s
-[Task 2/25] Current/Best: 17.40/ 22.19 GFLOPS | Progress: (12/20) | 8.28 s
-[Task 2/25] Current/Best: 16.17/ 22.19 GFLOPS | Progress: (16/20) | 10.42 s
-[Task 2/25] Current/Best: 10.55/ 22.19 GFLOPS | Progress: (20/20) | 13.51 s Done.
+[Task 2/25] Current/Best: 16.64/ 18.19 GFLOPS | Progress: (4/20) | 4.24 s
+[Task 2/25] Current/Best: 17.61/ 18.19 GFLOPS | Progress: (8/20) | 5.67 s
+[Task 2/25] Current/Best: 16.60/ 18.19 GFLOPS | Progress: (12/20) | 7.54 s
+[Task 2/25] Current/Best: 12.16/ 18.19 GFLOPS | Progress: (16/20) | 9.30 s
+[Task 2/25] Current/Best: 19.62/ 19.62 GFLOPS | Progress: (20/20) | 10.64 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 12.85/ 14.43 GFLOPS | Progress: (4/20) | 5.58 s
-[Task 3/25] Current/Best: 11.64/ 15.85 GFLOPS | Progress: (8/20) | 8.02 s
-[Task 3/25] Current/Best: 12.73/ 22.01 GFLOPS | Progress: (12/20) | 10.42 s
-[Task 3/25] Current/Best: 6.92/ 22.01 GFLOPS | Progress: (16/20) | 12.99 s
-[Task 3/25] Current/Best: 11.16/ 22.01 GFLOPS | Progress: (20/20) | 15.23 s Done.
+[Task 3/25] Current/Best: 9.98/ 15.77 GFLOPS | Progress: (4/20) | 5.25 s
+[Task 3/25] Current/Best: 14.87/ 24.24 GFLOPS | Progress: (8/20) | 7.12 s
+[Task 3/25] Current/Best: 22.50/ 24.24 GFLOPS | Progress: (12/20) | 10.50 s
+[Task 3/25] Current/Best: 1.62/ 24.24 GFLOPS | Progress: (16/20) | 14.25 s
+[Task 3/25] Current/Best: 8.21/ 24.24 GFLOPS | Progress: (20/20) | 16.91 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 18.11/ 18.11 GFLOPS | Progress: (4/20) | 5.35 s
-[Task 4/25] Current/Best: 13.31/ 18.11 GFLOPS | Progress: (8/20) | 7.28 s
-[Task 4/25] Current/Best: 10.42/ 18.11 GFLOPS | Progress: (12/20) | 9.59 s
-[Task 4/25] Current/Best: 14.34/ 18.11 GFLOPS | Progress: (16/20) | 11.57 s
-[Task 4/25] Current/Best: 6.14/ 18.11 GFLOPS | Progress: (20/20) | 17.02 s Done.
+[Task 4/25] Current/Best: 21.83/ 21.83 GFLOPS | Progress: (4/20) | 4.53 s
+[Task 4/25] Current/Best: 16.83/ 21.83 GFLOPS | Progress: (8/20) | 9.26 s
+[Task 4/25] Current/Best: 15.40/ 21.83 GFLOPS | Progress: (12/20) | 11.88 s
+[Task 4/25] Current/Best: 13.08/ 21.83 GFLOPS | Progress: (16/20) | 15.87 s
+[Task 4/25] Current/Best: 3.91/ 21.83 GFLOPS | Progress: (20/20) | 17.87 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 15.99/ 19.41 GFLOPS | Progress: (4/20) | 5.15 s
-[Task 5/25] Current/Best: 11.45/ 19.41 GFLOPS | Progress: (8/20) | 7.20 s
-[Task 5/25] Current/Best: 8.13/ 19.41 GFLOPS | Progress: (12/20) | 9.11 s
-[Task 5/25] Current/Best: 10.98/ 21.60 GFLOPS | Progress: (16/20) | 11.27 s
-[Task 5/25] Current/Best: 11.56/ 21.60 GFLOPS | Progress: (20/20) | 13.91 s Done.
+[Task 5/25] Current/Best: 5.67/ 18.50 GFLOPS | Progress: (4/20) | 4.80 s
+[Task 5/25] Current/Best: 15.71/ 19.80 GFLOPS | Progress: (8/20) | 6.91 s
+[Task 5/25] Current/Best: 4.16/ 19.80 GFLOPS | Progress: (12/20) | 9.08 s
+[Task 5/25] Current/Best: 11.40/ 19.80 GFLOPS | Progress: (16/20) | 11.48 s
+[Task 5/25] Current/Best: 14.70/ 19.80 GFLOPS | Progress: (20/20) | 14.11 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 7.04/ 17.47 GFLOPS | Progress: (4/20) | 5.92 s
-[Task 6/25] Current/Best: 11.08/ 17.47 GFLOPS | Progress: (8/20) | 12.03 s
-[Task 6/25] Current/Best: 14.69/ 17.47 GFLOPS | Progress: (12/20) | 15.72 s
-[Task 6/25] Current/Best: 10.08/ 17.47 GFLOPS | Progress: (16/20) | 18.31 s
-[Task 6/25] Current/Best: 9.68/ 22.51 GFLOPS | Progress: (20/20) | 25.78 s Done.
+[Task 6/25] Current/Best: 12.76/ 15.51 GFLOPS | Progress: (4/20) | 5.96 s
+[Task 6/25] Current/Best: 15.44/ 15.51 GFLOPS | Progress: (8/20) | 9.27 s
+[Task 6/25] Current/Best: 7.51/ 15.51 GFLOPS | Progress: (12/20) | 12.40 s
+[Task 6/25] Current/Best: 11.81/ 18.30 GFLOPS | Progress: (16/20) | 14.43 s
+[Task 6/25] Current/Best: 17.16/ 18.30 GFLOPS | Progress: (20/20) | 17.75 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 21.11/ 21.11 GFLOPS | Progress: (4/20) | 4.71 s
-[Task 7/25] Current/Best: 18.09/ 21.11 GFLOPS | Progress: (8/20) | 6.90 s
-[Task 7/25] Current/Best: 11.91/ 21.11 GFLOPS | Progress: (12/20) | 9.41 s
-[Task 7/25] Current/Best: 7.82/ 21.11 GFLOPS | Progress: (16/20) | 12.90 s
-[Task 7/25] Current/Best: 18.85/ 21.11 GFLOPS | Progress: (20/20) | 15.55 s Done.
+[Task 7/25] Current/Best: 7.06/ 16.92 GFLOPS | Progress: (4/20) | 6.03 s
+[Task 7/25] Current/Best: 11.88/ 21.43 GFLOPS | Progress: (8/20) | 8.87 s
+[Task 7/25] Current/Best: 15.94/ 21.43 GFLOPS | Progress: (12/20) | 11.27 s
+[Task 7/25] Current/Best: 19.51/ 21.43 GFLOPS | Progress: (16/20) | 13.29 s
+[Task 7/25] Current/Best: 15.06/ 21.43 GFLOPS | Progress: (20/20) | 16.59 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 12.08/ 18.01 GFLOPS | Progress: (4/20) | 6.32 s
-[Task 8/25] Current/Best: 18.12/ 18.12 GFLOPS | Progress: (8/20) | 15.11 s
-[Task 8/25] Current/Best: 8.67/ 18.12 GFLOPS | Progress: (12/20) | 19.06 s
-[Task 8/25] Current/Best: 3.99/ 18.12 GFLOPS | Progress: (16/20) | 25.27 s
-[Task 8/25] Current/Best: 3.59/ 18.12 GFLOPS | Progress: (20/20) | 31.39 s Done.
+[Task 8/25] Current/Best: 8.57/ 14.25 GFLOPS | Progress: (4/20) | 5.54 s
+[Task 8/25] Current/Best: 10.44/ 16.87 GFLOPS | Progress: (8/20) | 11.05 s
+[Task 8/25] Current/Best: 9.75/ 18.27 GFLOPS | Progress: (12/20) | 14.29 s
+[Task 8/25] Current/Best: 18.52/ 18.52 GFLOPS | Progress: (16/20) | 17.80 s
+[Task 8/25] Current/Best: 4.56/ 18.52 GFLOPS | Progress: (20/20) | 21.63 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 8.48/ 22.77 GFLOPS | Progress: (4/20) | 10.66 s
-[Task 9/25] Current/Best: 16.51/ 22.77 GFLOPS | Progress: (8/20) | 18.28 s
-[Task 9/25] Current/Best: 9.93/ 22.77 GFLOPS | Progress: (12/20) | 29.47 s
-[Task 9/25] Current/Best: 17.14/ 22.77 GFLOPS | Progress: (16/20) | 32.36 s
-[Task 9/25] Current/Best: 17.78/ 22.77 GFLOPS | Progress: (20/20) | 34.66 s
+[Task 9/25] Current/Best: 7.11/ 15.16 GFLOPS | Progress: (4/20) | 8.12 s
+[Task 9/25] Current/Best: 15.68/ 18.80 GFLOPS | Progress: (8/20) | 10.09 s
+[Task 9/25] Current/Best: 12.97/ 18.80 GFLOPS | Progress: (12/20) | 21.21 s
+[Task 9/25] Current/Best: 6.47/ 18.80 GFLOPS | Progress: (16/20) | 29.26 s
+[Task 9/25] Current/Best: 10.58/ 18.80 GFLOPS | Progress: (20/20) | 34.82 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 4.20/ 14.36 GFLOPS | Progress: (4/20) | 4.83 s Done.
+[Task 10/25] Current/Best: 8.25/ 19.34 GFLOPS | Progress: (4/20) | 4.77 s Done.
-[Task 10/25] Current/Best: 14.08/ 14.36 GFLOPS | Progress: (8/20) | 7.14 s
-[Task 10/25] Current/Best: 8.33/ 18.36 GFLOPS | Progress: (12/20) | 8.75 s
-[Task 10/25] Current/Best: 12.15/ 18.36 GFLOPS | Progress: (16/20) | 10.33 s
-[Task 10/25] Current/Best: 10.22/ 18.36 GFLOPS | Progress: (20/20) | 12.33 s Done.
+[Task 10/25] Current/Best: 6.03/ 20.66 GFLOPS | Progress: (8/20) | 6.54 s
+[Task 10/25] Current/Best: 13.74/ 20.66 GFLOPS | Progress: (12/20) | 8.18 s
+[Task 10/25] Current/Best: 16.48/ 20.66 GFLOPS | Progress: (16/20) | 10.12 s
+[Task 10/25] Current/Best: 18.11/ 21.59 GFLOPS | Progress: (20/20) | 12.32 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 18.02/ 18.02 GFLOPS | Progress: (4/20) | 5.32 s
-[Task 11/25] Current/Best: 15.86/ 23.35 GFLOPS | Progress: (8/20) | 7.84 s
-[Task 11/25] Current/Best: 12.32/ 23.35 GFLOPS | Progress: (12/20) | 10.11 s
-[Task 11/25] Current/Best: 13.08/ 23.35 GFLOPS | Progress: (16/20) | 12.67 s
-[Task 11/25] Current/Best: 6.18/ 23.35 GFLOPS | Progress: (20/20) | 15.67 s Done.
+[Task 11/25] Current/Best: 18.00/ 18.59 GFLOPS | Progress: (4/20) | 4.77 s
+[Task 11/25] Current/Best: 22.31/ 22.31 GFLOPS | Progress: (8/20) | 7.48 s
+[Task 11/25] Current/Best: 14.88/ 22.31 GFLOPS | Progress: (12/20) | 9.86 s
+[Task 11/25] Current/Best: 16.00/ 22.31 GFLOPS | Progress: (16/20) | 12.81 s
+[Task 11/25] Current/Best: 6.94/ 22.31 GFLOPS | Progress: (20/20) | 15.51 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 18.20/ 18.86 GFLOPS | Progress: (4/20) | 5.51 s
-[Task 12/25] Current/Best: 10.70/ 20.26 GFLOPS | Progress: (8/20) | 12.03 s
-[Task 12/25] Current/Best: 9.49/ 20.26 GFLOPS | Progress: (12/20) | 21.63 s
-[Task 12/25] Current/Best: 17.66/ 20.26 GFLOPS | Progress: (16/20) | 24.30 s
-[Task 12/25] Current/Best: 10.25/ 20.26 GFLOPS | Progress: (20/20) | 32.28 s Done.
+[Task 12/25] Current/Best: 10.64/ 16.00 GFLOPS | Progress: (4/20) | 5.89 s
+[Task 12/25] Current/Best: 10.15/ 16.00 GFLOPS | Progress: (8/20) | 12.00 s
+[Task 12/25] Current/Best: 10.82/ 16.00 GFLOPS | Progress: (12/20) | 14.20 s
+[Task 12/25] Current/Best: 4.47/ 16.00 GFLOPS | Progress: (16/20) | 16.65 s
+[Task 12/25] Current/Best: 12.44/ 18.18 GFLOPS | Progress: (20/20) | 22.29 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 23.46/ 23.46 GFLOPS | Progress: (4/20) | 6.87 s
-[Task 13/25] Current/Best: 8.12/ 23.46 GFLOPS | Progress: (8/20) | 9.46 s
-[Task 13/25] Current/Best: 15.13/ 23.46 GFLOPS | Progress: (12/20) | 13.50 s
-[Task 13/25] Current/Best: 9.13/ 23.46 GFLOPS | Progress: (16/20) | 17.43 s
-[Task 13/25] Current/Best: 12.01/ 23.46 GFLOPS | Progress: (20/20) | 19.70 s Done.
+[Task 13/25] Current/Best: 10.76/ 14.70 GFLOPS | Progress: (4/20) | 6.49 s
+[Task 13/25] Current/Best: 5.17/ 21.53 GFLOPS | Progress: (8/20) | 9.56 s
+[Task 13/25] Current/Best: 23.21/ 23.21 GFLOPS | Progress: (12/20) | 12.28 s
+[Task 13/25] Current/Best: 13.29/ 23.21 GFLOPS | Progress: (16/20) | 14.66 s
+[Task 13/25] Current/Best: 18.27/ 23.21 GFLOPS | Progress: (20/20) | 16.86 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 15.28/ 15.28 GFLOPS | Progress: (4/20) | 5.59 s
-[Task 14/25] Current/Best: 12.96/ 15.28 GFLOPS | Progress: (8/20) | 11.00 s
-[Task 14/25] Current/Best: 14.32/ 15.28 GFLOPS | Progress: (12/20) | 14.33 s
-[Task 14/25] Current/Best: 16.81/ 21.33 GFLOPS | Progress: (16/20) | 18.09 s
-[Task 14/25] Current/Best: 16.86/ 21.33 GFLOPS | Progress: (20/20) | 20.37 s
+[Task 14/25] Current/Best: 5.44/ 16.41 GFLOPS | Progress: (4/20) | 5.42 s
+[Task 14/25] Current/Best: 3.98/ 17.85 GFLOPS | Progress: (8/20) | 10.39 s
+[Task 14/25] Current/Best: 11.97/ 17.85 GFLOPS | Progress: (12/20) | 12.90 s
+[Task 14/25] Current/Best: 18.96/ 18.96 GFLOPS | Progress: (16/20) | 15.19 s
+[Task 14/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (20/20) | 17.68 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 22.96/ 22.96 GFLOPS | Progress: (4/20) | 4.44 s
-[Task 15/25] Current/Best: 5.49/ 22.96 GFLOPS | Progress: (8/20) | 8.45 s
-[Task 15/25] Current/Best: 16.25/ 22.96 GFLOPS | Progress: (12/20) | 12.66 s
-[Task 15/25] Current/Best: 11.68/ 22.96 GFLOPS | Progress: (16/20) | 15.02 s
-[Task 15/25] Current/Best: 19.45/ 22.96 GFLOPS | Progress: (20/20) | 17.81 s
-[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 16/25] Current/Best: 7.44/ 15.28 GFLOPS | Progress: (4/20) | 4.78 s
-[Task 16/25] Current/Best: 9.46/ 15.28 GFLOPS | Progress: (8/20) | 7.17 s
-[Task 16/25] Current/Best: 10.65/ 21.04 GFLOPS | Progress: (12/20) | 8.97 s
-[Task 16/25] Current/Best: 6.13/ 21.04 GFLOPS | Progress: (16/20) | 10.60 s
-[Task 16/25] Current/Best: 16.32/ 21.04 GFLOPS | Progress: (20/20) | 13.78 s Done.
+[Task 15/25] Current/Best: 15.94/ 15.94 GFLOPS | Progress: (4/20) | 7.07 s
+[Task 15/25] Current/Best: 18.47/ 18.47 GFLOPS | Progress: (8/20) | 8.96 s
+[Task 15/25] Current/Best: 13.48/ 18.47 GFLOPS | Progress: (12/20) | 12.74 s
+[Task 15/25] Current/Best: 15.36/ 18.47 GFLOPS | Progress: (16/20) | 18.47 s
+[Task 15/25] Current/Best: 18.46/ 18.47 GFLOPS | Progress: (20/20) | 21.25 s
+[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 16/25] Current/Best: 15.21/ 20.71 GFLOPS | Progress: (4/20) | 5.57 s
+[Task 16/25] Current/Best: 13.30/ 20.71 GFLOPS | Progress: (8/20) | 7.48 s
+[Task 16/25] Current/Best: 10.34/ 20.71 GFLOPS | Progress: (12/20) | 10.30 s
+[Task 16/25] Current/Best: 19.61/ 20.71 GFLOPS | Progress: (16/20) | 12.30 s
+[Task 16/25] Current/Best: 16.79/ 20.71 GFLOPS | Progress: (20/20) | 14.87 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 11.90/ 15.25 GFLOPS | Progress: (4/20) | 5.36 s
-[Task 17/25] Current/Best: 13.14/ 15.25 GFLOPS | Progress: (8/20) | 8.06 s
-[Task 17/25] Current/Best: 10.04/ 22.50 GFLOPS | Progress: (12/20) | 10.56 s
-[Task 17/25] Current/Best: 9.28/ 22.50 GFLOPS | Progress: (16/20) | 13.92 s
-[Task 17/25] Current/Best: 19.61/ 22.50 GFLOPS | Progress: (20/20) | 16.20 s Done.
+[Task 17/25] Current/Best: 24.06/ 24.06 GFLOPS | Progress: (4/20) | 5.27 s
+[Task 17/25] Current/Best: 20.42/ 24.06 GFLOPS | Progress: (8/20) | 7.24 s
+[Task 17/25] Current/Best: 20.85/ 24.06 GFLOPS | Progress: (12/20) | 9.25 s
+[Task 17/25] Current/Best: 4.57/ 24.06 GFLOPS | Progress: (16/20) | 12.02 s
+[Task 17/25] Current/Best: 5.22/ 24.06 GFLOPS | Progress: (20/20) | 14.74 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 10.33/ 17.81 GFLOPS | Progress: (4/20) | 5.49 s
-[Task 18/25] Current/Best: 15.28/ 17.81 GFLOPS | Progress: (8/20) | 13.69 s
-[Task 18/25] Current/Best: 15.46/ 17.81 GFLOPS | Progress: (12/20) | 16.80 s
-[Task 18/25] Current/Best: 17.28/ 17.81 GFLOPS | Progress: (16/20) | 19.61 s
-[Task 18/25] Current/Best: 8.46/ 19.69 GFLOPS | Progress: (20/20) | 25.22 s Done.
+[Task 18/25] Current/Best: 9.54/ 14.70 GFLOPS | Progress: (4/20) | 5.51 s
+[Task 18/25] Current/Best: 4.22/ 17.42 GFLOPS | Progress: (8/20) | 11.65 s
+[Task 18/25] Current/Best: 17.73/ 17.73 GFLOPS | Progress: (12/20) | 14.01 s
+[Task 18/25] Current/Best: 13.22/ 17.73 GFLOPS | Progress: (16/20) | 16.56 s
+[Task 18/25] Current/Best: 8.88/ 17.73 GFLOPS | Progress: (20/20) | 22.20 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 5.25/ 18.67 GFLOPS | Progress: (4/20) | 5.88 s
-[Task 19/25] Current/Best: 5.28/ 18.67 GFLOPS | Progress: (8/20) | 9.01 s
-[Task 19/25] Current/Best: 10.38/ 21.72 GFLOPS | Progress: (12/20) | 11.35 s
-[Task 19/25] Current/Best: 18.11/ 21.72 GFLOPS | Progress: (16/20) | 13.80 s
-[Task 19/25] Current/Best: 1.55/ 21.72 GFLOPS | Progress: (20/20) | 19.32 s Done.
+[Task 19/25] Current/Best: 21.36/ 21.36 GFLOPS | Progress: (4/20) | 6.94 s
+[Task 19/25] Current/Best: 18.28/ 21.36 GFLOPS | Progress: (8/20) | 10.61 s Done.
+ Done.
+
+[Task 19/25] Current/Best: 12.89/ 22.40 GFLOPS | Progress: (12/20) | 14.30 s
+[Task 19/25] Current/Best: 19.24/ 22.40 GFLOPS | Progress: (16/20) | 17.07 s
+[Task 19/25] Current/Best: 9.31/ 22.40 GFLOPS | Progress: (20/20) | 19.54 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 6.86/ 15.80 GFLOPS | Progress: (4/20) | 4.89 s
-[Task 20/25] Current/Best: 10.68/ 15.80 GFLOPS | Progress: (8/20) | 8.45 s
-[Task 20/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (12/20) | 12.79 s
-[Task 20/25] Current/Best: 7.54/ 20.66 GFLOPS | Progress: (16/20) | 16.90 s
-[Task 20/25] Current/Best: 15.16/ 20.66 GFLOPS | Progress: (20/20) | 19.94 s
+[Task 20/25] Current/Best: 10.62/ 13.04 GFLOPS | Progress: (4/20) | 5.18 s
+[Task 20/25] Current/Best: 17.87/ 17.87 GFLOPS | Progress: (8/20) | 7.70 s
+[Task 20/25] Current/Best: 12.66/ 17.87 GFLOPS | Progress: (12/20) | 11.12 s
+[Task 20/25] Current/Best: 14.60/ 17.87 GFLOPS | Progress: (16/20) | 13.94 s
+[Task 20/25] Current/Best: 6.17/ 18.06 GFLOPS | Progress: (20/20) | 16.21 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 14.32/ 18.18 GFLOPS | Progress: (4/20) | 5.64 s Done.
-
-[Task 21/25] Current/Best: 22.55/ 22.55 GFLOPS | Progress: (8/20) | 7.49 s
-[Task 21/25] Current/Best: 19.48/ 22.55 GFLOPS | Progress: (12/20) | 10.37 s
-[Task 21/25] Current/Best: 2.72/ 22.55 GFLOPS | Progress: (16/20) | 14.26 s
-[Task 21/25] Current/Best: 16.97/ 22.55 GFLOPS | Progress: (20/20) | 18.73 s
+[Task 21/25] Current/Best: 2.73/ 17.99 GFLOPS | Progress: (4/20) | 5.17 s
+[Task 21/25] Current/Best: 9.50/ 17.99 GFLOPS | Progress: (8/20) | 9.37 s
+[Task 21/25] Current/Best: 7.19/ 19.80 GFLOPS | Progress: (12/20) | 12.45 s
+[Task 21/25] Current/Best: 10.04/ 19.80 GFLOPS | Progress: (16/20) | 15.64 s
+[Task 21/25] Current/Best: 2.47/ 19.80 GFLOPS | Progress: (20/20) | 17.65 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 14.37/ 14.37 GFLOPS | Progress: (4/20) | 6.41 s
-[Task 22/25] Current/Best: 12.89/ 14.37 GFLOPS | Progress: (8/20) | 8.88 s
-[Task 22/25] Current/Best: 12.20/ 18.31 GFLOPS | Progress: (12/20) | 10.74 s
-[Task 22/25] Current/Best: 2.66/ 20.97 GFLOPS | Progress: (16/20) | 12.89 s
-[Task 22/25] Current/Best: 10.02/ 20.97 GFLOPS | Progress: (20/20) | 14.65 s Done.
+[Task 22/25] Current/Best: 9.74/ 17.39 GFLOPS | Progress: (4/20) | 6.26 s Done.
+ Done.
+
+[Task 22/25] Current/Best: 7.49/ 17.39 GFLOPS | Progress: (8/20) | 8.46 s
+[Task 22/25] Current/Best: 2.76/ 17.39 GFLOPS | Progress: (12/20) | 11.49 s
+[Task 22/25] Current/Best: 9.87/ 18.82 GFLOPS | Progress: (16/20) | 14.43 s
+[Task 22/25] Current/Best: 15.64/ 18.82 GFLOPS | Progress: (20/20) | 17.19 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 9.57/ 21.58 GFLOPS | Progress: (4/20) | 5.95 s
-[Task 23/25] Current/Best: 1.55/ 21.58 GFLOPS | Progress: (8/20) | 10.16 s
-[Task 23/25] Current/Best: 11.27/ 21.58 GFLOPS | Progress: (12/20) | 12.52 s
-[Task 23/25] Current/Best: 21.78/ 21.78 GFLOPS | Progress: (16/20) | 14.71 s
-[Task 23/25] Current/Best: 6.14/ 22.48 GFLOPS | Progress: (20/20) | 17.62 s Done.
+[Task 23/25] Current/Best: 9.61/ 19.93 GFLOPS | Progress: (4/20) | 6.10 s
+[Task 23/25] Current/Best: 21.79/ 21.79 GFLOPS | Progress: (8/20) | 10.12 s
+[Task 23/25] Current/Best: 19.87/ 21.79 GFLOPS | Progress: (12/20) | 13.89 s
+[Task 23/25] Current/Best: 8.82/ 21.79 GFLOPS | Progress: (16/20) | 16.80 s
+[Task 23/25] Current/Best: 22.16/ 24.03 GFLOPS | Progress: (20/20) | 19.00 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 3.30/ 9.58 GFLOPS | Progress: (4/20) | 13.84 s
-[Task 24/25] Current/Best: 9.40/ 9.58 GFLOPS | Progress: (8/20) | 24.81 s
-[Task 24/25] Current/Best: 6.25/ 9.58 GFLOPS | Progress: (12/20) | 27.57 s
-[Task 24/25] Current/Best: 5.11/ 9.58 GFLOPS | Progress: (16/20) | 37.95 s
-[Task 24/25] Current/Best: 9.23/ 9.58 GFLOPS | Progress: (20/20) | 50.51 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 25/25] Current/Best: 2.98/ 4.10 GFLOPS | Progress: (4/20) | 15.10 s
-[Task 25/25] Current/Best: 1.55/ 7.84 GFLOPS | Progress: (8/20) | 27.08 s
-[Task 25/25] Current/Best: 4.31/ 7.84 GFLOPS | Progress: (12/20) | 32.84 s
-[Task 25/25] Current/Best: 8.30/ 8.30 GFLOPS | Progress: (16/20) | 34.87 s
-[Task 25/25] Current/Best: 9.23/ 9.23 GFLOPS | Progress: (20/20) | 45.83 s
+[Task 24/25] Current/Best: 3.05/ 4.13 GFLOPS | Progress: (4/20) | 8.99 s
+[Task 24/25] Current/Best: 3.84/ 7.18 GFLOPS | Progress: (8/20) | 12.36 s
+[Task 24/25] Current/Best: 6.25/ 10.46 GFLOPS | Progress: (12/20) | 23.30 s
+[Task 24/25] Current/Best: 3.75/ 10.46 GFLOPS | Progress: (16/20) | 34.28 s
+[Task 24/25] Current/Best: 2.34/ 10.46 GFLOPS | Progress: (20/20) | 46.59 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 7.34/ 7.93 GFLOPS | Progress: (4/20) | 13.66 s Done.
+
+[Task 25/25] Current/Best: 7.70/ 9.73 GFLOPS | Progress: (8/20) | 24.32 s
+[Task 25/25] Current/Best: 3.04/ 9.73 GFLOPS | Progress: (12/20) | 36.90 s
+[Task 25/25] Current/Best: 1.55/ 10.11 GFLOPS | Progress: (16/20) | 47.87 s
+[Task 25/25] Current/Best: 2.53/ 10.11 GFLOPS | Progress: (20/20) | 58.83 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -948,8 +948,8 @@ 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
@@ -986,8 +986,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 398.90424599999733, 'median': 397.49282374999666, 'std': 3.5888206502880196}
-unoptimized: {'mean': 512.6999624700011, 'median': 512.9441132000068, 'std': 1.2014829374162335}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 410.20361767999475, 'median': 408.73830729999554, 'std': 3.347262406241466}
+unoptimized: {'mean': 509.58684035999795, 'median': 508.9386698999931, 'std': 2.6515574204392656}
</pre></div>
</div>
</div>
@@ -1001,7 +1001,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 13 minutes 7.761 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 33.459 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 8b42143dfe..f81aaf7dfc 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -543,7 +543,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.369e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.485e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 307ce25550..7a8aa6b3a6 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -513,7 +513,7 @@ class Module:
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x104a78f0)), stage(b, placeholder(b, 0x22dfe710)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attr [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xbcb9f50)), stage(b, placeholder(b, 0x229e9200)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index b25d845155..d89453a568 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>16:59.897</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>16:15.127</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,35 +354,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>13:07.761</p></td>
+<td><p>12:33.459</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>01:35.957</p></td>
+<td><p>01:31.657</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>01:03.088</p></td>
+<td><p>00:57.137</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:37.236</p></td>
+<td><p>00:36.368</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>00:33.042</p></td>
+<td><p>00:33.652</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>00:01.763</p></td>
+<td><p>00:01.844</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>00:00.859</p></td>
+<td><p>00:00.841</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.190</p></td>
+<td><p>00:00.168</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 01da5c135d..9b113d80e2 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -554,8 +554,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
-naive: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000012
+naive: 0.000009
</pre></div>
</div>
</div>
@@ -649,7 +649,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000032
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000025
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -686,10 +686,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.367289999820059e-06 1.0
- naive 6.8297e-06 0.9270301562944869
-parallel 7.4248e-06 1.007806126836509
- vector 3.18535e-05 4.323638678642758
+ numpy 1.2035689999265741e-05 1.0
+ naive 8.8403e-06 0.734507120118524
+parallel 6.9763000000000004e-06 0.5796344040454351
+ vector 2.45827e-05 2.0424836466791447
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1005,7 +1005,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018865
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017709
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1046,7 +1046,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.568804
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.088310
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1110,7 +1110,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.293213
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.289019
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1159,7 +1159,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.332215
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.334241
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1208,7 +1208,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.119187
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.113900
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1278,7 +1278,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109593
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108426
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1344,7 +1344,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111158
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110020
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1401,7 +1401,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.147267
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145530
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1454,13 +1454,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.5688042943 1.0
- blocking 0.2932132598 0.0821600837760458
- vectorization 0.3322146373 0.09308849964975789
-loop permutation 0.1191874021 0.033397012632596014
- array packing 0.1095930104 0.030708607522984394
- block caching 0.1111575985 0.031147014331253182
- parallelization 0.1472671276 0.041265117236944364
+ none 3.0883096068 1.0
+ blocking 0.2890188348 0.09358479932310651
+ vectorization 0.3342410449 0.10822782928371259
+loop permutation 0.11389982540000002 0.03688096075251311
+ array packing 0.1084264876 0.03510868449240352
+ block caching 0.11001961810000001 0.03562454290779432
+ parallelization 0.14552988640000003 0.04712282929132648
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1492,7 +1492,6 @@ 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 3.088 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>