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 2023/01/05 02:00:03 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@bf0607bd317a7db8eba1a91c12170934c1ad201f)
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 27b66cd8f7 deploying docs (apache/tvm@bf0607bd317a7db8eba1a91c12170934c1ad201f)
27b66cd8f7 is described below
commit 27b66cd8f72cdffaf1febfb455443f6095740799
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Jan 5 01:59:57 2023 +0000
deploying docs (apache/tvm@bf0607bd317a7db8eba1a91c12170934c1ad201f)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 322643 -> 330120 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23935 -> 23754 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.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 | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 506 +++++++++++---
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 39 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 742 +++++++++++++++------
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 12 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 38 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 506 +++++++++++---
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 39 +-
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 742 +++++++++++++++------
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 ++--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 274 ++++----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
130 files changed, 2789 insertions(+), 1415 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index cb959f7e7c..749f250b96 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 c36f44d737..eb961b1b9c 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 2d1de06d59..2dc1002fb4 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -315,7 +315,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.639 seconds)
+ **Total running time of the script:** ( 1 minutes 8.545 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 24d0c9987d..02c796ada9 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -228,7 +228,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 969ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 937ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index fe751d4924..8692933434 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf79b09cf-0b43-4d0e-a19e-72a9d1e9a937 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf91ff55f-ac6c-4063-9162-858a3678bd8d 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 b41d7dcc87..abc46ff8d6 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -116,7 +116,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 67.3MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 48.9MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 52.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 59.1MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 62.8MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 60.9MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 8.03M/41.5M [00:00<00:00, 84.2MB/s]
39%|###8 | 16.1M/41.5M [00:00<00:00, 38.2MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 49.0MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 57.4MB/s]
93%|#########2| 38.5M/41.5M [00:00<00:00, 56.0MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 54.1MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 2327cae7b8..64dd524838 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -98,7 +98,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
32%|###2 | 14.3M/44.7M [00:00<00:00, 143MB/s]
63%|######2 | 27.9M/44.7M [00:00<00:00, 109MB/s]
87%|########6 | 38.7M/44.7M [00:00<00:00, 110MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 105MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 66.2MB/s]
49%|####9 | 22.0M/44.7M [00:00<00:00, 109MB/s]
74%|#######3 | 32.9M/44.7M [00:00<00:00, 80.7MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 94.1MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 91.1MB/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 e65754ae34..34a9d21c5c 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -416,7 +416,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 15.071 seconds)
+ **Total running time of the script:** ( 1 minutes 10.810 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 0af72743db..135b27b60b 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:51.751** total execution time for **how_to_compile_models** files:
+**05:37.514** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:15.071 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:10.810 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:11.639 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:08.545 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:48.431 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:45.698 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.706 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.767 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.597 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:28.497 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:27.125 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:25.793 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.035 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:25.143 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.845 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:22.333 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.845 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.515 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.457 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.413 | 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 78d9a0e655..425e684487 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -723,7 +723,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2806.9997 2807.6032 2811.0758 2803.7583 2.1930
+ 2755.6715 2754.1031 2767.5189 2751.3624 4.3784
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 58c6422599..4912892165 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -433,7 +433,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4209 16.4410 16.7418 16.0910 0.2278
+ 16.1268 15.7303 19.0033 15.4902 1.0054
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 9ea171b446..89934aa732 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -127,7 +127,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
9%|9 | 15.6M/170M [00:00<00:00, 164MB/s]
18%|#8 | 31.3M/170M [00:00<00:01, 104MB/s]
25%|##4 | 42.4M/170M [00:00<00:01, 95.7MB/s]
31%|### | 52.1M/170M [00:00<00:01, 94.5MB/s]
36%|###6 | 61.4M/170M [00:00<00:01, 93.2MB/s]
42%|####2 | 72.0M/170M [00:00<00:01, 86.1MB/s]
47%|####7 | 80.4M/170M [00:00<00:01, 70.9MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 69.9MB/s]
58%|#####8 | 98.7M/170M [00:01<00:00, 80.3MB/s]
66%|######5 | 112M/170M [00:01<00:00, 88.6MB/s]
74%|#######4 | 126M/170M [00:01<00:00, 104MB/s]
80%|######## | 137M/170M [00:01<00:00, 87.4MB/s]
86%|########5 | 146M/170M [00:01<00:00, 84.0MB/s]
91%|#########1| 155M/170M [00:01<00:00, 88.5MB/s]
99%|#########8| 168M/170M [00:01<00:00, 99.6MB/s]
100%|##########| 170M/170M [00:01<00:00, 91.3MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 58.4MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 59.6MB/s]
14%|#4 | 24.0M/170M [00:00<00:02, 67.7MB/s]
18%|#8 | 30.6M/170M [00:00<00:02, 62.4MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 62.7MB/s]
29%|##8 | 49.1M/170M [00:00<00:01, 71.6MB/s]
33%|###3 | 56.1M/170M [00:00<00:01, 69.2MB/s]
38%|###7 | 64.0M/170M [00:00<00:01, 71.6MB/s]
43%|####3 | 73.1M/170M [00:01<00:01, 78.4MB/s]
48%|####7 | 80.8M/170M [00:01<00:01, 60.1MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 58.6MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 58.4MB/s]
61%|######1 | 104M/170M [00:01<00:01, 60.9MB/s]
69%|######9 | 118M/170M [00:01<00:00, 81.0MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 82.6MB/s]
80%|######## | 136M/170M [00:02<00:00, 74.3MB/s]
85%|########4 | 144M/170M [00:02<00:00, 75.9MB/s]
93%|#########2| 158M/170M [00:02<00:00, 92.8MB/s]
98%|#########8| 167M/170M [00:02<00:00, 56.1MB/s]
100%|##########| 170M/170M [00:02<00:00, 66.2MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -296,7 +296,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 12.631 seconds)
+ **Total running time of the script:** ( 3 minutes 11.699 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 2a4a0c993e..95f25c6c48 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -236,7 +236,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 64.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 57.3MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
60%|#####9 | 8.12M/13.6M [00:00<00:00, 74.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 86.9MB/s]
@@ -418,7 +418,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3247 90.2200 91.9962 90.0500 0.2935
+ 90.5344 90.4058 94.1261 90.0283 0.7032
@@ -467,7 +467,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.540 seconds)
+ **Total running time of the script:** ( 1 minutes 5.287 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 31895a68f0..aefe7369af 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -432,7 +432,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.5761 119.5501 120.5232 118.6987 0.3760
+ 119.2738 119.2231 121.0559 117.5871 0.5324
@@ -469,7 +469,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 30.015 seconds)
+ **Total running time of the script:** ( 2 minutes 26.963 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 70786c219e..1edc699a00 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -253,7 +253,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 23.861 seconds)
+ **Total running time of the script:** ( 1 minutes 29.751 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 35b379f957..1810f94b68 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -166,7 +166,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6358/132723 [00:00<00:01, 63552.03KB/s]
11%|#1 | 14950/132723 [00:00<00:01, 76699.68KB/s]
17%|#7 | 22621/132723 [00:00<00:01, 67068.57KB/s]
24%|##3 | 31237/132723 [00:00<00:01, 74000.15KB/s]
30%|##9 | 39745/132723 [00:00<00:01, 77775.85KB/s]
36%|###6 | 48353/132723 [00:00<00:01, 80496.74KB/s]
43%|####2 | 56484/132723 [00:00<00:01, 74310.50KB/s]
49%|####8 | 65025/132723 [00:00<00:00, 77588.33KB/s]
55%|#####5 | 73620/132723 [00:00<00:00, 80067.31KB/s]
62%|######1 | 82230/132723 [00:01<00:00, 81862.25KB/s]
68%|######8 | 90487/132723 [00:01<00:00, 75469.36KB/s]
75%|#######4 | 99090/132723 [00:01<00:00, 78441.69KB/s]
81%|########1 | 107725/132723 [00:01<00:00, 80706.55KB/s]
88%|########7 | 116333/132723 [00:01<00:00, 82266.50KB/s]
94%|#########4| 124973/132723 [00:01<00:00, 83474.44KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 79005.53KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5946/132723 [00:00<00:02, 59456.51KB/s]
10%|# | 13803/132723 [00:00<00:01, 70695.64KB/s]
16%|#6 | 21655/132723 [00:00<00:01, 74266.67KB/s]
22%|##2 | 29474/132723 [00:00<00:01, 75812.53KB/s]
28%|##8 | 37330/132723 [00:00<00:01, 76801.81KB/s]
34%|###3 | 45073/132723 [00:00<00:01, 77012.85KB/s]
40%|###9 | 52829/132723 [00:00<00:01, 77188.25KB/s]
46%|####5 | 60677/132723 [00:00<00:00, 77595.42KB/s]
52%|#####1 | 68536/132723 [00:00<00:00, 77905.12KB/s]
58%|#####7 | 76355/132723 [00:01<00:00, 77992.16KB/s]
63%|######3 | 84220/132723 [00:01<00:00, 78188.26KB/s]
69%|######9 | 92039/132723 [00:01<00:00, 78120.94KB/s]
75%|#######5 | 99852/132723 [00:01<00:00, 78084.82KB/s]
81%|########1 | 107661/132723 [00:01<00:00, 77891.75KB/s]
87%|########7 | 115486/132723 [00:01<00:00, 77997.78KB/s]
93%|#########
2| 123320/132723 [00:01<00:00, 78093.70KB/s]
99%|#########8| 131130/132723 [00:01<00:00, 78046.60KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77075.80KB/s]
@@ -242,7 +242,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 11.798 seconds)
+ **Total running time of the script:** ( 3 minutes 3.244 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 6458e6382f..76e2a83535 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**13:48.577** total execution time for **how_to_deploy_models** files:
+**13:35.475** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:12.631 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:11.699 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:11.798 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:03.244 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:30.015 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:26.963 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:23.861 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:29.751 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.540 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.287 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.236 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:53.720 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:36.651 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:34.792 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.913 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:25.095 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.925 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:24.917 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 4dbbe1eaa0..c077720217 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -472,7 +472,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip76ded8db-3ddc-4079-a899-ee22f9540099 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip932c3960-6925-42b9-a6dc-715b267d6e4b 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 800723721b..d3d91d5e0f 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:49.492** total execution time for **how_to_extend_tvm** files:
+**00:46.738** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:45.767 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:43.336 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.600 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.385 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.117 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.010 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 9ba0211e4c..0c13aa089f 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 7700us [7700us] (46.47%; 46.47%)
- FoldScaleAxis: 8870us [9us] (53.53%; 53.53%)
- FoldConstant: 8862us [1749us] (53.48%; 99.90%)
- InferType: 7113us [7113us] (42.93%; 80.27%)
+ InferType: 7220us [7220us] (46.63%; 46.63%)
+ FoldScaleAxis: 8262us [7us] (53.37%; 53.37%)
+ FoldConstant: 8256us [1691us] (53.32%; 99.92%)
+ InferType: 6564us [6564us] (42.40%; 79.51%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 7342us [7342us] (44.98%; 44.98%)
- FoldScaleAxis: 8980us [8us] (55.02%; 55.02%)
- FoldConstant: 8972us [1878us] (54.97%; 99.91%)
- InferType: 7094us [7094us] (43.46%; 79.07%)
+ InferType: 6583us [6583us] (45.02%; 45.02%)
+ FoldScaleAxis: 8040us [4us] (54.98%; 54.98%)
+ FoldConstant: 8036us [1665us] (54.95%; 99.95%)
+ InferType: 6371us [6371us] (43.57%; 79.28%)
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 6533f26573..a01539a782 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 35.912033 ms
+ Convolution: 34.155872 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 fb97ae4f5a..55f86880fe 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -657,7 +657,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.184669 ms
+ conv2d with tensor core: 13.336589 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 2a13a18119..2769ca9621 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.017942
- Baseline: 3.372778
+ Numpy running time: 0.017974
+ Baseline: 3.206709
@@ -238,7 +238,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.322392
+ Opt1: 0.300285
@@ -340,7 +340,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.335350
+ Opt2: 0.328322
@@ -435,7 +435,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.123002
+ Opt3: 0.114948
@@ -559,7 +559,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109568
+ Opt4: 0.109372
@@ -680,7 +680,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111175
+ Opt5: 0.111690
@@ -804,7 +804,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.149820
+ Opt6: 0.146278
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 d438ee0c60..ddb55fef1e 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
=================
-**00:35.298** total execution time for **how_to_optimize_operators** files:
+**00:34.109** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.558 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.510 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.600 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.542 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.139 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.057 | 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 b4e8e3a110..55d879974d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:23.581** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:11.353** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:41.707 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:45.315 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:33.935 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:31.063 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:02.919 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:01.136 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:40.896 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:30.982 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:12.379 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:11.852 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.745 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:11.006 | 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 dd9d5b2f71..36b00b2fa8 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
@@ -239,49 +239,238 @@ cooperative fetching, unrolling and operator fusion.
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- for (xx.inner.init: int32, 0, 7) {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[xx.inner.init] = 0f32
- conv2d_nchw_1[(xx.inner.init + 7)] = 0f32
- }
- for (rc.outer.outer: int32, 0, 64) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 3) {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_1, 8)) < 81), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_1)] = @tir.if_then_else(((((9 <= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*62) + threadIdx.x_1), 81)) && (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*62) + threadIdx.x_1), 81) < 72)) && (1 <= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + threadIdx.x_1), 9))) && (floormod(((ax0.ax1.fused. [...]
- }
- }
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1: int32, 0, 4) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 6) {
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 32)) < 24), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*1344) + (threadIdx.x_2*6)) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*294912) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*72)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*448) + [...]
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [6144]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ for (rc.outer.outer: int32, 0, 8) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*3136)
+ let cse_var_1: int32 = (rc.outer.outer*576)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 1364)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2744), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2940), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3136), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3332), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 2736)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3724), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3920), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
}
- }
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 2) {
- for (ry.inner: int32, 0, 3) {
- for (xx.inner: int32, 0, 7) {
- let cse_var_1: int32 = (xx.inner + 7)
- {
- conv2d_nchw_1[xx.inner] = (conv2d_nchw_1[xx.inner] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.inner) + rx.outer.inner)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_1] = (conv2d_nchw_1[cse_var_1] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.inner) + rx.outer.inner)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner) + 2304)]))
- }
- }
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1764), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 12), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2156), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 44), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2548), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2940), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 20), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3332), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 68), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3528), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3724), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 76), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4116), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 28), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4312), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4508), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 92), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4704), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4900)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4900), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 100), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5096)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5096), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5292)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5292), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 36), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5488)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5488), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5684)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5684), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5880)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5880), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 68), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 6076)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6076), 192)*4608)) + cse_var_1) + (floordiv((threadIdx.x_2 + 124), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ }
+ for (rc.outer.inner: int32, 0, 16) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3072)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 192)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3264)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3073)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 193)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3265)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3074)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 194)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3266)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3075)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 195)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3267)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3076)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 196)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3268)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3077)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 197)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3269)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3078)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 198)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3270)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3079)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 199)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3271)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3080)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 200)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3272)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3081)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 201)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3273)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3082)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 202)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3274)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3083)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 203)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3275)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 384)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3456)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 576)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3648)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 385)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3457)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 577)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3649)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 386)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3458)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 578)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3650)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 387)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3459)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 579)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3651)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 388)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3460)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 580)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3652)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 389)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3461)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 581)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3653)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 390)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3462)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 582)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3654)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 391)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3463)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 583)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3655)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 392)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3464)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 584)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3656)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 393)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3465)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 585)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3657)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 394)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3466)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 586)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3658)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 395)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3467)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 587)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3659)]))
}
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*3136) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*64) + floordiv(threadIdx.x, 7))]), 0f32)
- compute_3[((((blockIdx.x*3136) + (threadIdx.x*7)) + i3.inner) + 1568)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias_3[(((blockIdx.x*64) + floordiv(threadIdx.x, 7)) + 32)]), 0f32)
+ for (i1.inner: int32, 0, 4) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 16)]), 0f32)
}
}
}
@@ -336,7 +525,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.372 ms
+ Execution time of this operator: 0.363 ms
@@ -384,36 +573,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=4)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
- conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
+ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ 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=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -431,16 +620,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=6)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -458,45 +647,182 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[4608];
- for (int xx_inner_init = 0; xx_inner_init < 7; ++xx_inner_init) {
- conv2d_nchw[xx_inner_init] = 0.000000e+00f;
- conv2d_nchw[(xx_inner_init + 7)] = 0.000000e+00f;
- }
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 3; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 3)) < 81) {
- pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x))] = (((((9 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62) + ((int)threadIdx.x)) % 81)) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62) + ((int)threadIdx.x)) % 81) < 72)) && (1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx.x)) % 9))) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx.x)) % 9) < 8)) ? data[(((((r [...]
+ extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[6144];
+ 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[7] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 112) {
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
}
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 < 4; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1) {
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 6; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 5)) < 24) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 1344) + (((int)threadIdx.x) * 6)) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 448) + (((int)threadIdx.x) * 2)) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s / 3)) % 24) * 3)) + (ax0_a [...]
- }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 4) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 8) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 4) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 16) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 20) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 8) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 28) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 32) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 12) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 40) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 44) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 16) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 52) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 56) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 20) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 64) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3332) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 68) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3528) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 24) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3724) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 76) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 80) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4116) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 28) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4312) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 88) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4508) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 92) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4704) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4900)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4900) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 100) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5096)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5096) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 104) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5292)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5292) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 36) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5488)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5488) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5684)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5684) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 116) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5880)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5880) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 40) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 68) {
+ kernel_shared[(((int)threadIdx.x) + 6076)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6076) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 124) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
}
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 2; ++rc_inner) {
- for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
- for (int xx_inner = 0; xx_inner < 7; ++xx_inner) {
- conv2d_nchw[xx_inner] = (conv2d_nchw[xx_inner] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_inner) + rx_outer_inner)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[(xx_inner + 7)] = (conv2d_nchw[(xx_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_inner) + rx_outer_inner)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner) + 2304)]));
- }
- }
- }
+ __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 * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3072)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 192)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3264)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3073)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 193)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3265)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3074)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 194)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3266)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3075)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 195)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3267)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3076)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 196)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3268)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3077)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 197)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3269)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3078)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 198)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3270)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3079)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 199)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3271)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3080)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 200)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3272)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3081)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 201)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3273)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3082)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 202)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3274)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3083)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 203)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3275)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 384)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3456)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 576)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3648)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 385)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3457)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 577)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3649)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 386)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3458)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 578)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3650)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 387)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3459)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 579)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3651)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 388)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3460)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 580)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3652)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 389)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3461)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 581)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3653)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 390)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3462)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 582)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3654)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 391)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3463)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 583)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3655)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 392)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3464)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 584)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3656)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 393)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3465)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 585)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3657)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 394)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3466)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 586)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3658)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 395)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3467)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 587)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3659)]));
}
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 3136) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 3136) + (((int)threadIdx.x) * 7)) + i3_inner) + 1568)] = max((conv2d_nchw[(i3_inner + 7)] + bias[(((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7)) + 32)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 16)]), 0.000000e+00f);
}
}
@@ -558,7 +884,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 41.707 seconds)
+ **Total running time of the script:** ( 5 minutes 45.315 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 d34ba560f7..f9ddff499c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -643,7 +643,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8856 7.8856 7.8875 7.8839 0.0015
+ 7.8911 7.8909 7.8937 7.8885 0.0021
@@ -671,7 +671,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.919 seconds)
+ **Total running time of the script:** ( 1 minutes 1.136 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 1150487d5c..6d923cc2cd 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -662,7 +662,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 768.8948 768.5418 772.1388 766.0039 2.5170
+ 748.8933 748.5468 749.8692 748.2639 0.6997
@@ -690,7 +690,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.935 seconds)
+ **Total running time of the script:** ( 1 minutes 31.063 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 f5367fbe18..865f1034e8 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -386,27 +386,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.inner.init: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[((i.inner.init*16) + j.init)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 32) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = ((i.inner*16) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
+ for (i0.outer: int32, 0, 4) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [1024], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((i0.outer*8192) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32)) + i1.inner)
+ compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_4]), 0f32)
+ }
}
}
}
@@ -462,7 +467,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.665 ms
+ Execution time of this operator: 1.698 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 ed51b3af17..7f382bdbb6 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:47.003** total execution time for **how_to_tune_with_autotvm** files:
+**00:49.273** 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``) | 00:46.966 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:49.238 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
++--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 1b71cdef5f..bd5d890b79 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -265,8 +265,7 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 44.48/44.48 result: MeasureResult(costs=(0.005204324333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.942298650741577, timestamp=1672879982.3740249) [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9387861
- No: 2 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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
@@ -388,8 +387,8 @@ 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3905470
- No: 3 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5188327
+ 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -511,8 +510,8 @@ 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, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9864484
- No: 4 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4397165
+ No: 3 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -634,8 +633,8 @@ 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, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7637503
- No: 5 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9055567
+ No: 4 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -757,8 +756,8 @@ 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, 2, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1909563
- No: 6 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4972076
+ No: 5 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -880,10 +879,8 @@ 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, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8986874
- No: 7 GFLOPS: 26.75/44.48 result: MeasureResult(costs=(0.00865332025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.840994358062744, timestamp=1672879990.439722) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3141163
- No: 8 GFLOPS: 28.72/44.48 result: MeasureResult(costs=(0.008059667692307692,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2247412204742432, timestamp=1672879991.2185087) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5495480
- No: 9 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8385233
+ No: 6 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1005,8 +1002,9 @@ 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, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1081533
- No: 10 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3731290
+ No: 7 GFLOPS: 1.80/1.80 result: MeasureResult(costs=(0.1288972625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4602324962615967, timestamp=1672882308.158129) [('tile_f', [-1, 32, 2, 4]), ('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', 0), ('unroll_explicit', 0)],None,389293
+ No: 8 GFLOPS: 0.00/1.80 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
@@ -1128,27 +1126,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2497385
- No: 11 GFLOPS: 8.19/44.48 result: MeasureResult(costs=(0.0282496565,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.6270527839660645, timestamp=1672880002.2008271) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8881246
- No: 12 GFLOPS: 0.00/44.48 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, 4, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9996030
- No: 13 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3019588
+ No: 9 GFLOPS: 0.00/1.80 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
@@ -1270,8 +1249,162 @@ 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, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2127140
- No: 14 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3480006
+ No: 10 GFLOPS: 0.00/1.80 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 357, in evaluator
+ blob = feval(*args)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 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 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 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: 0x00007f5da4569fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 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, 8, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,676998
+ No: 11 GFLOPS: 219.15/219.15 result: MeasureResult(costs=(0.0010563536736842105,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8245925903320312, timestamp=1672882323.4235377) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3955680
+ No: 12 GFLOPS: 0.00/219.15 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
@@ -1393,8 +1526,8 @@ 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, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1659133
- No: 15 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9971620
+ No: 13 GFLOPS: 0.00/219.15 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
@@ -1516,8 +1649,8 @@ 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, 128, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8096227
- No: 16 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5509336
+ No: 14 GFLOPS: 0.00/219.15 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
@@ -1639,161 +1772,395 @@ 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, 256, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7727563
- No: 17 GFLOPS: 0.00/44.48 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 357, in evaluator
- blob = feval(*args)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3321061
+ No: 15 GFLOPS: 0.00/219.15 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_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 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/./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):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 23: 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:
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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):
- 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 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
+ 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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, 32, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5981585
+ No: 16 GFLOPS: 0.00/219.15 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_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 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: 0x00007f5b5d5c6fa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
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
+ 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):
- 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, 4, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2259318
- No: 18 GFLOPS: 0.00/44.48 result: 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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, 32, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9402657
+ No: 17 GFLOPS: 0.00/219.15 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_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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, 16, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1574204
+ No: 18 GFLOPS: 0.00/219.15 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, 64, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9297490
+ No: 19 GFLOPS: 0.00/219.15 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
@@ -1915,9 +2282,8 @@ 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, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6114857
- No: 19 GFLOPS: 235.08/235.08 result: MeasureResult(costs=(0.0009847759333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3667175769805908, timestamp=1672880011.0845015) [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3531310
- No: 20 GFLOPS: 0.00/235.08 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 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,6834654
+ No: 20 GFLOPS: 0.00/219.15 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
@@ -2039,7 +2405,7 @@ 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, 32, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3656909
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,342716
@@ -2094,9 +2460,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3531310
+ [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3955680
Finish loading 20 records
- Time cost of this operator: 0.001410
+ Time cost of this operator: 0.001515
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 85474b8d8d..77560e51fa 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.5 98.708 (1, 2, 10, 10, 3) 2 1 [312.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.111 0.983 (1, 6, 10, 10) 1 1 [3.111]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.981 0.31 (1, 1, 10, 10, 3) 1 1 [0.981]
- Total_time - 316.592 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.2 98.73 (1, 2, 10, 10, 3) 2 1 [311.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.958 (1, 6, 10, 10) 1 1 [3.021]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.982 0.312 (1, 1, 10, 10, 3) 1 1 [0.982]
+ Total_time - 315.203 - - - - -
@@ -397,10 +397,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.3 97.289 (1, 6, 10, 10, 1) 2 1 [100.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.81 1.756 (1, 6, 10, 10) 1 1 [1.81]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.955 (1, 1, 10, 10, 3) 1 1 [0.984]
- Total_time - 103.095 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 115.4 97.768 (1, 6, 10, 10, 1) 2 1 [115.4]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.784 1.512 (1, 6, 10, 10) 1 1 [1.784]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.851 0.721 (1, 3, 10, 10, 1) 1 1 [0.851]
+ Total_time - 118.035 - - - - -
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 ce21b0f6a4..4beb8f55d8 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -109,7 +109,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|###### | 2.09M/3.42M [00:00<00:00, 16.7MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 25.1MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 80.9MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -314,7 +314,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.460 seconds)
+ **Total running time of the script:** ( 1 minutes 1.876 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 08da405542..37b1856e90 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpwftzjw4b/images/random'
+ '/tmp/tmp4jvlr05e/images/random'
@@ -316,7 +316,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [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], [1.0, 0.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpwftzjw4b/images/target contains 8144 images
- /tmp/tmpwftzjw4b/images/random contains 5000 images
+ /tmp/tmp4jvlr05e/images/target contains 8144 images
+ /tmp/tmp4jvlr05e/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2124 - accuracy: 0.9283 - val_loss: 0.1220 - val_accuracy: 0.9588 - 47s/epoch - 144ms/step
+ 328/328 - 47s - loss: 0.2343 - accuracy: 0.9174 - val_loss: 0.1764 - val_accuracy: 0.9449 - 47s/epoch - 142ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.0956 - accuracy: 0.9637 - val_loss: 0.1147 - val_accuracy: 0.9619 - 44s/epoch - 133ms/step
+ 328/328 - 44s - loss: 0.0970 - accuracy: 0.9649 - val_loss: 0.1839 - val_accuracy: 0.9422 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 44s - loss: 0.0630 - accuracy: 0.9763 - val_loss: 0.1039 - val_accuracy: 0.9653 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0676 - accuracy: 0.9743 - val_loss: 0.1062 - val_accuracy: 0.9619 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7fa0ab739610>
+ <keras.callbacks.History object at 0x7f385773f990>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 18.778 seconds)
+ **Total running time of the script:** ( 4 minutes 21.101 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 fae15acb77..7cd30ced8a 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:31.986** total execution time for **how_to_work_with_microtvm** files:
+**06:25.205** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:18.778 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:21.101 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:07.460 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:01.876 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:53.517 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.767 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.303 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.693 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.926 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.765 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 609a31d434..76a91dd556 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.836** total execution time for **how_to_work_with_relay** files:
+**00:43.964** 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``) | 00:32.613 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.081 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.588 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.089 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.627 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.787 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 5be6ca9b80..14306f2169 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7fa0ab9584d0>
+ <function my_cuda_math_rule at 0x7f3851776170>
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 9c22e9416c..29ff896156 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:06.541** total execution time for **how_to_work_with_schedules** files:
+**00:07.606** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.014 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.144 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.167 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.115 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.581 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.579 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.564 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.554 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.113 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.112 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.023 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 0951d51130..90d7c13228 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -343,7 +343,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpvhov1_tz/input0.cc'\nsource_filename = \"/tmp/tmpvhov1_tz/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpwtgp1e3q/input0.cc'\nsource_filename = \"/tmp/tmpwtgp1e3q/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 777f148ad2..27a753eb6e 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
=================
-**00:27.254** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:25.886** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:27.248 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:25.880 | 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 d111acc770..872a4ca8d2 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -289,7 +289,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 30.21s!
+ resnet18_v1 inference graph built in 28.43s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
index 6744b998c7..bb4f36a79f 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -333,7 +333,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 20.47s!
+ yolov3-tiny inference graph built in 19.28s!
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 b22dbe1512..b76a08e5c2 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
=================
-**01:42.356** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.206** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:52.085 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:45.962 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.271 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:45.244 | 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 fbeed43814..b6814ec097 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
=================
-**00:03.211** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.182** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.737 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.725 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.474 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.458 | 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 6d683f135e..742d5e6a81 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
=================
-**00:00.852** total execution time for **topic_vta_tutorials** files:
+**00:00.800** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.456 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.422 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.396 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.379 | 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 d7ddcf90ce..282f1c92a7 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -203,13 +203,6 @@ trials, we can load the best schedule from the log file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- .T
-
-
@@ -332,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.587 ms
+ Execution time of this operator: 95.405 ms
@@ -450,7 +443,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 29.595 seconds)
+ **Total running time of the script:** ( 1 minutes 16.697 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 dafa66b0f7..6d9747c23d 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -450,16 +450,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 12.62/12.62 result: MeasureResult(costs=(0.0212750562,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7127289772033691, timestamp=1672878546.5182264) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
- No: 2 GFLOPS: 3.28/12.62 result: MeasureResult(costs=(0.0818079904,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5599911212921143, timestamp=1672878548.0807588) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
- No: 3 GFLOPS: 2.83/12.62 result: MeasureResult(costs=(0.0947567186,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7626209259033203, timestamp=1672878550.6288085) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
- No: 4 GFLOPS: 9.69/12.62 result: MeasureResult(costs=(0.0276888212,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8194856643676758, timestamp=1672878551.3305037) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
- No: 5 GFLOPS: 4.09/12.62 result: MeasureResult(costs=(0.0656034804,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3047773838043213, timestamp=1672878552.7669842) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
- No: 6 GFLOPS: 9.77/12.62 result: MeasureResult(costs=(0.0274755166,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7110121250152588, timestamp=1672878554.2572384) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
- No: 7 GFLOPS: 4.15/12.62 result: MeasureResult(costs=(0.0646942704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2955398559570312, timestamp=1672878556.3292017) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
- No: 8 GFLOPS: 2.22/12.62 result: MeasureResult(costs=(0.1209604482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1650946140289307, timestamp=1672878558.5155125) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
- No: 9 GFLOPS: 14.36/14.36 result: MeasureResult(costs=(0.0186932454,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5641310214996338, timestamp=1672878559.1960435) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
- No: 10 GFLOPS: 7.46/14.36 result: MeasureResult(costs=(0.035994663,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7751169204711914, timestamp=1672878560.0260532) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+ No: 1 GFLOPS: 12.40/12.40 result: MeasureResult(costs=(0.0216470044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6152174472808838, timestamp=1672880904.961685) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+ No: 2 GFLOPS: 14.34/14.34 result: MeasureResult(costs=(0.0187140628,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6137557029724121, timestamp=1672880905.5090969) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+ No: 3 GFLOPS: 1.22/14.34 result: MeasureResult(costs=(0.2195632924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7343947887420654, timestamp=1672880910.0190434) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
+ No: 4 GFLOPS: 1.64/14.34 result: MeasureResult(costs=(0.16361529660000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.837488889694214, timestamp=1672880912.8840718) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 5 GFLOPS: 3.05/14.34 result: MeasureResult(costs=(0.08789075560000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6464266777038574, timestamp=1672880914.7544508) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+ No: 6 GFLOPS: 13.88/14.34 result: MeasureResult(costs=(0.0193371728,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5762917995452881, timestamp=1672880916.068992) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+ No: 7 GFLOPS: 1.18/14.34 result: MeasureResult(costs=(0.227297203,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.9153645038604736, timestamp=1672880920.7527018) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+ No: 8 GFLOPS: 12.80/14.34 result: MeasureResult(costs=(0.020963635799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6822052001953125, timestamp=1672880921.3441238) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+ No: 9 GFLOPS: 2.82/14.34 result: MeasureResult(costs=(0.0950836638,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.727813959121704, timestamp=1672880923.186269) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+ No: 10 GFLOPS: 11.37/14.34 result: MeasureResult(costs=(0.023602291,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5843014717102051, timestamp=1672880923.8179212) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 98e8576cb7..b52c9dc3c4 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -320,7 +320,7 @@ standard deviation.
.. code-block:: none
- {'mean': 515.7709692800006, 'median': 515.0009511999997, 'std': 2.2209522109315}
+ {'mean': 512.1992977499997, 'median': 511.0846481500005, 'std': 2.718325039446462}
@@ -554,30 +554,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 9.24/ 22.32 GFLOPS | Progress: (4/20) | 7.75 s
[Task 1/25] Current/Best: 11.26/ 22.32 GFLOPS | Progress: (8/20) | 10.85 s
[Task 1/25] Current/Best: 13.52/ 22.32 GFLOPS | Progress: (12/20) | 13.63 s
[Task 1/25] Current/Best: 23.55/ 23.55 GFLOPS | Progress: (16/20) | 17.19 s
[Task 1/25] Current/Best: 14.41/ 23.55 GFLOPS | Progress: (20/20) | 20.13 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 9.99/ 13.02 GFLOPS | Progress: (4/20) | 4.10 s
[Task 2/25] Current/Best: 15.99/ 15.99 GFLOPS | Progress: (8/20) | 6.47 s
[Task 2/25] Current/Best: 16.72/ 16.72 GFLOPS | Progress: (12/20) | 8.09 s
[Task 2/25] Current/Best: 7.00/ 23.11 GFLOPS | Progress: (16/20) | 10.13 s
[Task 2/25] Current/Best: 6.38/ 23.11 GFLOPS | Progress: (20/20) | 13.42 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.53/ 14.53 GFLOPS | Progress: (4/20) | 4.09 s
[Task 3/25] Current/Best: 19.15/ 19.91 GFLOPS | Progress: (8/20) | 6.43 s
[Task 3/25] Current/Best: 5.42/ 19.91 GFLOPS | Progress: (12/20) | 10.57 s
[Task 3/25] Current/Best: 17.95/ 19.91 GFLOPS | Progress: (16/20) | 13.52 s
[Task 3/25] Current/Best: 8.57/ 19.91 GFLOPS | Progress: (20/20) | 16.12 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 12.24/ 13.41 GFLOPS | Progress: (4/20) | 4.88 s
[Task 4/25] Current/Best: 17.29/ 17.29 GFLOPS | Progress: (8/20) | 10.41 s
[Task 4/25] Current/Best: 9.97/ 17.29 GFLOPS | Progress: (12/20) | 12.69 s
[Task 4/25] Current/Best: 5.74/ 17.29 GFLOPS | Progress: (16/20) | 15.05 s
[Task 4/25] Current/Best: 17.47/ 17.47 GFLOPS | Progress: (20/20) | 18.48 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.11/ 11.15 GFLOPS | Progress: (4/20) | 4.26 s
[Task 5/25] Current/Best: 7.73/ 22.19 GFLOPS | Progress: (8/20) | 5.90 s
[Task 5/25] Current/Best: 4.58/ 22.19 GFLOPS | Progress: (12/20) | 8.72 s
[Task 5/25] Current/Best: 14.28/ 22.19 GFLOPS | Progress: (16/20) | 11.13 s
[Task 5/25] Current/Best: 17.82/ 22.19 GFLOPS | Progress: (20/20) | 12.85 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.84/ 17.04 GFLOPS | Progress: (4/20) | 4.29 s
[Task 6/25] Current/Best: 13.56/ 18.23 GFLOPS | Progress: (8/20) | 6.89 s
[Task 6/25] Current/Best: 12.85/ 18.23 GFLOPS | Progress: (12/20) | 9.64 s
[Task 6/25] Current/Best: 3.70/ 18.23 GFLOPS | Progress: (16/20) | 12.40 s
[Task 6/25] Current/Best: 21.86/ 21.86 GFLOPS | Progress: (20/20) | 14.71 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.80/ 15.90 GFLOPS | Progress: (4/20) | 5.62 s
[Task 7/25] Current/Best: 22.90/ 22.90 GFLOPS | Progress: (8/20) | 7.58 s
[Task 7/25] Current/Best: 14.96/ 22.90 GFLOPS | Progress: (12/20) | 9.96 s
[Task 7/25] Current/Best: 8.71/ 22.90 GFLOPS | Progress: (16/20) | 14.23 s
[Task 7/25] Current/Best: 6.22/ 22.90 GFLOPS | Progress: (20/20) | 16.87 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 7.19/ 13.81 GFLOPS | Progress: (4/20) | 4.24 s
[Task 8/25] Current/Best: 7.64/ 16.39 GFLOPS | Progress: (8/20) | 15.99 s
[Task 8/25] Current/Best: 13.62/ 17.86 GFLOPS | Progress: (12/20) | 20.09 s
[Task 8/25] Current/Best: 10.90/ 17.86 GFLOPS | Progress: (16/20) | 26.16 s
[Task 8/25] Current/Best: 16.35/ 17.86 GFLOPS | Progress: (20/20) | 30.07 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 7.70/ 17.90 GFLOPS | Progress: (4/20) | 5.71 s
[Task 9/25] Current/Best: 9.30/ 17.90 GFLOPS | Progress: (8/20) | 7.32 s
[Task 9/25] Current/Best: 20.53/ 20.53 GFLOPS | Progress: (12/20) | 9.16 s
[Task 9/25] Current/Best: 9.18/ 20.53 GFLOPS | Progress: (16/20) | 20.31 s
[Task 9/25] Current/Best: 16.33/ 20.53 GFLOPS | Progress: (20/20
) | 31.43 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 3.14/ 11.87 GFLOPS | Progress: (4/20) | 4.50 s Done.
- Done.
-
[Task 10/25] Current/Best: 8.04/ 15.44 GFLOPS | Progress: (8/20) | 6.27 s
[Task 10/25] Current/Best: 7.88/ 18.49 GFLOPS | Progress: (12/20) | 10.09 s
[Task 10/25] Current/Best: 18.93/ 18.93 GFLOPS | Progress: (16/20) | 11.96 s
[Task 10/25] Current/Best: 11.22/ 18.93 GFLOPS | Progress: (20/20) | 13.97 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 23.73/ 23.73 GFLOPS | Progress: (4/20) | 4.40 s
[Task 11/25] Current/Best: 15.72/ 23.73 GFLOPS | Progress: (8/20) | 6.90 s
[Task 11/25] Current/Best: 21.51/ 23.73 GFLOPS | Progress: (12/20) | 9.43 s
[Task 11/25] Current/Best: 17.40/ 23.73 GFLOPS | Progress: (16/20) | 11.38 s
[Task 11/25] Current/Best: 23.19/ 23.73 GFLOPS | Progress: (20/20) | 13.37 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 10.07/ 19.30 GFLOPS | Progress: (4/20) | 4.51 s
[Task 12/25] Current/Best: 15.84/ 19.30 GFLOPS | Progress: (8/20) | 8.14 s
[Task 12/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (12/20) | 11.87 s
[Task 12/25] Current/Best: 5.11/ 20.66 GFLOPS | Progress: (16/20) | 14.20 s
[Task 12/25] Current/Best: 15.43/ 20.66 GFLOPS | Progress: (20/20) | 21.44 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 7.37/ 17.24 GFLOPS | Progress: (4/20) | 5.10 s
[Task 13/25] Current/Best: 17.48/ 17.48 GFLOPS | Progress: (8/20) | 8.70 s
[Task 13/25] Current/Best: 3.10/ 20.62 GFLOPS | Progress: (12/20) | 12.38 s
[Task 13/25] Current/Best: 3.09/ 20.62 GFLOPS | Progress: (16/20) | 15.49 s
[Task 13/25] Current/Best: 8.74/ 20.62 GFLOPS | Progress: (20/20) | 19.27 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.40/ 12.53 GFLOPS | Progress: (4/20) | 4.38 s
[Task 14/25] Current/Best: 15.51/ 18.28 GFLOPS | Progress: (8/20) | 10.40 s
[Task 14/25] Current/Best: 14.74/ 18.28 GFLOPS | Progress: (12/20) | 13.82 s
[Task 14/25] Current/Best: 11.09/ 18.28 GFLOPS | Progress: (16/20) | 16.77 s
[Task 14/25] Current/Best: 4.88/ 18.28 GFLOPS | Progress: (20/20) | 20.61 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 20.14/ 20.14 GFLOPS | Progress: (4/20) | 5.16 s
[Task 15/25] Current/Best: 21.21/ 21.21 GFLOPS | Progress: (8/20) | 7.39 s
[Task 15/25] Current/Best: 5.71/ 21.21 GFLOPS | Progress: (12/20) | 14.86 s
[Task 15/25] Current/Best: 16.92/ 21.21 GFLOPS | Progress: (16/20) | 16.63 s
[Task 15/25] Current/Best: 12.51/ 21.21 GFLOPS | Progress: (20/2
0) | 18.24 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 15.81/ 15.81 GFLOPS | Progress: (4/20) | 4.47 s
[Task 16/25] Current/Best: 13.17/ 21.12 GFLOPS | Progress: (8/20) | 6.80 s Done.
- Done.
-
[Task 16/25] Current/Best: 10.57/ 21.12 GFLOPS | Progress: (12/20) | 9.65 s
[Task 16/25] Current/Best: 16.73/ 21.12 GFLOPS | Progress: (16/20) | 13.67 s
[Task 16/25] Current/Best: 10.24/ 21.12 GFLOPS | Progress: (20/20) | 15.59 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 20.14/ 21.92 GFLOPS | Progress: (4/20) | 4.33 s
[Task 17/25] Current/Best: 17.78/ 21.92 GFLOPS | Progress: (8/20) | 6.66 s
[Task 17/25] Current/Best: 17.84/ 21.92 GFLOPS | Progress: (12/20) | 9.39 s
[Task 17/25] Current/Best: 8.77/ 21.92 GFLOPS | Progress: (16/20) | 11.91 s
[Task 17/25] Current/Best: 9.90/ 21.92 GFLOPS | Progress: (20/20) | 15.36 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 15.86/ 15.86 GFLOPS | Progress: (4/20) | 8.41 s
[Task 18/25] Current/Best: 17.87/ 17.95 GFLOPS | Progress: (8/20) | 10.41 s
[Task 18/25] Current/Best: 11.67/ 18.76 GFLOPS | Progress: (12/20) | 13.04 s
[Task 18/25] Current/Best: 13.48/ 18.76 GFLOPS | Progress: (16/20) | 15.76 s
[Task 18/25] Current/Best: 19.88/ 20.35 GFLOPS | Progress: (20/20) | 18.15 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 17.61/ 18.46 GFLOPS | Progress: (4/20) | 6.23 s
[Task 19/25] Current/Best: 10.93/ 18.46 GFLOPS | Progress: (8/20) | 10.23 s
[Task 19/25] Current/Best: 12.40/ 21.03 GFLOPS | Progress: (12/20) | 12.97 s
[Task 19/25] Current/Best: 21.53/ 21.53 GFLOPS | Progress: (16/20) | 15.46 s
[Task 19/25] Current/Best: 18.53/ 21.53 GFLOPS | Progress: (20/20) | 18.18 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.00/ 12.20 GFLOPS | Progress: (4/20) | 5.63 s
[Task 20/25] Current/Best: 5.33/ 12.53 GFLOPS | Progress: (8/20) | 8.23 s
[Task 20/25] Current/Best: 15.05/ 15.05 GFLOPS | Progress: (12/20) | 11.47 s
[Task 20/25] Current/Best: 15.41/ 15.90 GFLOPS | Progress: (16/20) | 13.95 s
[Task 20/25] Current/Best: 9.58/ 16.13 GFLOPS | Progress: (20/20) | 16.76 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 17.79/ 17.79 GFLOPS | Progress: (4/20) | 7.40 s
[Task 21/25] Current/Best: 12.38/ 19.19 GFLOPS | Progress: (8/20) | 9.33 s
[Task 21/25] Current/Best: 16.61/ 19.19 GFLOPS | Progress: (12/20) | 11.92 s
[Task 21/25] Current/Best: 14.35/ 19.19 GFLOPS | Progress: (16/20) | 14.19 s Done.
-
[Task 21/25] Current/Best: 5.35/ 19.19 GFLOPS | Progress: (20/20) | 15.64 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (4/20) | 4.73 s
[Task 22/25] Current/Best: 10.14/ 19.01 GFLOPS | Progress: (8/20) | 7.51 s
[Task 22/25] Current/Best: 6.67/ 20.06 GFLOPS | Progress: (12/20) | 9.97 s
[Task 22/25] Current/Best: 14.75/ 20.55 GFLOPS | Progress: (16/20) | 11.59 s
[Task 22/25] Current/Best: 15.34/ 20.55 GFLOPS | Progress: (20/20) | 15.82 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 1.55/ 23.38 GFLOPS | Progress: (4/20) | 5.84 s
[Task 23/25] Current/Best: 10.66/ 23.38 GFLOPS | Progress: (8/20) | 8.51 s
[Task 23/25] Current/Best: 1.55/ 23.38 GFLOPS | Progress: (12/20) | 12.80 s
[Task 23/25] Current/Best: 19.41/ 23.38 GFLOPS | Progress: (16/20) | 20.74 s
[Task 23/25] Current/Best: 17.82/ 23.38 GFLOPS | Progress: (20/20) | 23.33 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 5.65/ 5.77 GFLOPS | Progress: (4/20) | 12.52 s
[Task 24/25] Current/Best: 2.93/ 8.73 GFLOPS | Progress: (8/20) | 19.77 s
[Task 24/25] Current/Best: 6.78/ 8.73 GFLOPS | Progress: (12/20) | 30.75 s
[Task 24/25] Current/Best: 3.09/ 8.77 GFLOPS | Progress: (16/20) | 41.41 s
[Task 24/25] Current/Best: 1.70/ 8.77 GFLOPS | Progress: (20/20) | 53.61 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 2.99/ 8.53 GFLOPS | Progress: (4/20) | 12.82 s
[Task 25/25] Current/Best: 7.88/ 8.53 GFLOPS | Progress: (8/20) | 23.79 s
[Task 25/25] Current/Best: 1.55/ 8.63 GFLOPS | Progress: (12/20) | 34.76 s
[Task 25/25] Current/Best: 8.72/ 8.72 GFLOPS | Progress: (16/20) | 38.97 s
[Task 25/25] Current/Best: 5.62/ 9.21 GFLOPS | Progress: (20/20) | 40.35 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.45/ 19.03 GFLOPS | Progress: (4/20) | 7.34 s
[Task 1/25] Current/Best: 22.90/ 22.90 GFLOPS | Progress: (8/20) | 11.82 s
[Task 1/25] Current/Best: 11.67/ 22.90 GFLOPS | Progress: (12/20) | 15.25 s
[Task 1/25] Current/Best: 12.34/ 22.90 GFLOPS | Progress: (16/20) | 17.76 s
[Task 1/25] Current/Best: 7.15/ 22.90 GFLOPS | Progress: (20/20) | 20.17 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 5.70/ 14.21 GFLOPS | Progress: (4/20) | 4.10 s
[Task 2/25] Current/Best: 6.25/ 16.86 GFLOPS | Progress: (8/20) | 5.74 s
[Task 2/25] Current/Best: 6.55/ 16.86 GFLOPS | Progress: (12/20) | 7.57 s
[Task 2/25] Current/Best: 8.14/ 16.86 GFLOPS | Progress: (16/20) | 9.51 s
[Task 2/25] Current/Best: 21.40/ 21.40 GFLOPS | Progress: (20/20) | 11.51 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 15.27/ 16.85 GFLOPS | Progress: (4/20) | 3.98 s
[Task 3/25] Current/Best: 13.51/ 22.07 GFLOPS | Progress: (8/20) | 6.52 s
[Task 3/25] Current/Best: 15.21/ 22.07 GFLOPS | Progress: (12/20) | 9.12 s
[Task 3/25] Current/Best: 12.66/ 22.07 GFLOPS | Progress: (16/20) | 11.61 s
[Task 3/25] Current/Best: 6.21/ 22.07 GFLOPS | Progress: (20/20) | 13.79 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 10.97/ 15.40 GFLOPS | Progress: (4/20) | 7.82 s
[Task 4/25] Current/Best: 8.13/ 19.55 GFLOPS | Progress: (8/20) | 10.65 s
[Task 4/25] Current/Best: 10.03/ 19.55 GFLOPS | Progress: (12/20) | 15.74 s
[Task 4/25] Current/Best: 9.75/ 19.55 GFLOPS | Progress: (16/20) | 18.45 s
[Task 4/25] Current/Best: 17.34/ 19.55 GFLOPS | Progress: (20/20) | 20.57 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.14/ 19.09 GFLOPS | Progress: (4/20) | 3.98 s
[Task 5/25] Current/Best: 10.33/ 19.09 GFLOPS | Progress: (8/20) | 6.28 s
[Task 5/25] Current/Best: 13.30/ 20.65 GFLOPS | Progress: (12/20) | 8.74 s
[Task 5/25] Current/Best: 5.67/ 20.65 GFLOPS | Progress: (16/20) | 11.69 s
[Task 5/25] Current/Best: 8.50/ 20.65 GFLOPS | Progress: (20/20) | 13.53 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 16.67/ 16.67 GFLOPS | Progress: (4/20) | 7.06 s
[Task 6/25] Current/Best: 21.94/ 21.94 GFLOPS | Progress: (8/20) | 9.41 s
[Task 6/25] Current/Best: 17.94/ 21.94 GFLOPS | Progress: (12/20) | 11.87 s
[Task 6/25] Current/Best: 15.14/ 21.94 GFLOPS | Progress: (16/20) | 14.80 s
[Task 6/25] Current/Best: 5.57/ 21.94 GFLOPS | Progress: (20/20) | 18.71 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.20/ 19.34 GFLOPS | Progress: (4/20) | 3.71 s
[Task 7/25] Current/Best: 12.11/ 19.34 GFLOPS | Progress: (8/20) | 6.98 s
[Task 7/25] Current/Best: 10.29/ 19.34 GFLOPS | Progress: (12/20) | 9.04 s
[Task 7/25] Current/Best: 8.57/ 19.34 GFLOPS | Progress: (16/20) | 11.57 s
[Task 7/25] Current/Best: 16.96/ 19.34 GFLOPS | Progress: (20/20) | 13.92 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 15.47/ 15.47 GFLOPS | Progress: (4/20) | 7.27 s
[Task 8/25] Current/Best: 10.92/ 15.47 GFLOPS | Progress: (8/20) | 10.73 s
[Task 8/25] Current/Best: 12.39/ 15.47 GFLOPS | Progress: (12/20) | 14.05 s
[Task 8/25] Current/Best: 5.19/ 15.79 GFLOPS | Progress: (16/20) | 20.29 s
[Task 8/25] Current/Best: 15.01/ 18.50 GFLOPS | Progress: (20/20) | 26.28 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 7.67/ 10.51 GFLOPS | Progress: (4/20) | 9.85 s
[Task 9/25] Current/Best: 14.15/ 14.51 GFLOPS | Progress: (8/20) | 13.63 s
[Task 9/25] Current/Best: 6.97/ 22.46 GFLOPS | Progress: (12/20) | 15.28 s
[Task 9/25] Current/Best: 22.33/ 22.46 GFLOPS | Progress: (16/20) | 16.82 s
[Task 9/25] Current/Best: 16.76/ 22.46 GFLOPS | Progress: (20/20) | 18.80 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 2.98/ 17.65 GFLOPS | Progress: (4/20) | 4.28 s
[Task 10/25] Current/Best: 8.36/ 17.65 GFLOPS | Progress: (8/20) | 6.22 s
[Task 10/25] Current/Best: 14.58/ 17.65 GFLOPS | Progress: (12/20) | 8.61 s
[Task 10/25] Current/Best: 3.28/ 17.65 GFLOPS | Progress: (16/20) | 10.56 s
[Task 10/25] Current/Best: 10.28/ 17.65 GFLOPS | Progress: (20/20) | 12.43 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 9.29/ 23.55 GFLOPS | Progress: (4/20) | 4.06 s
[Task 11/25] Current/Best: 15.86/ 23.55 GFLOPS | Progress: (8/20) | 6.33 s
[Task 11/25] Current/Best: 1.57/ 23.55 GFLOPS | Progress: (12/20) | 9.85 s
[Task 11/25] Current/Best: 12.33/ 23.55 GFLOPS | Progress: (16/20) | 12.27 s
[Task 11/25] Current/Best: 22.32/ 23.55 GFLOPS | Progress: (20/20) | 14.37 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 4.39/ 20.86 GFLOPS | Progress: (4/20) | 4.17 s
[Task 12/25] Current/Best: 14.61/ 20.86 GFLOPS | Progress: (8/20) | 6.42 s
[Task 12/25] Current/Best: 10.34/ 20.86 GFLOPS | Progress: (12/20) | 9.82 s
[Task 12/25] Current/Best: 13.98/ 20.86 GFLOPS | Progress: (16/20) | 12.15 s
[Task 12/25] Current/Best: 10.42/ 20.86 GFLOPS | Progress: (20/20) | 14.48 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.31/ 10.23 GFLOPS | Progress: (4/20) | 5.39 s
[Task 13/25] Current/Best: 6.91/ 18.36 GFLOPS | Progress: (8/20) | 8.53 s
[Task 13/25] Current/Best: 7.46/ 18.36 GFLOPS | Progress: (12/20) | 11.32 s
[Task 13/25] Current/Best: 6.12/ 19.30 GFLOPS | Progress: (16/20) | 13.98 s
[Task 13/25] Current/Best: 16.69/ 19.30 GFLOPS | Progress: (20/20) | 16.76 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 11.56/ 16.72 GFLOPS | Progress: (4/20) | 5.46 s
[Task 14/25] Current/Best: 9.70/ 16.72 GFLOPS | Progress: (8/20) | 8.13 s
[Task 14/25] Current/Best: 11.16/ 21.93 GFLOPS | Progress: (12/20) | 10.04 s
[Task 14/25] Current/Best: 3.15/ 21.93 GFLOPS | Progress: (16/20) | 12.88 s
[Task 14/25] Current/Best: 10.68/ 21.93 GFLOPS | Progress: (20/20) | 15.69 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 13.30/ 15.41 GFLOPS | Progress: (4/20) | 3.90 s
[Task 15/25] Current/Best: 11.19/ 15.41 GFLOPS | Progress: (8/20) | 6.90 s
[Task 15/25] Current/Best: 14.53/ 15.41 GFLOPS | Progress: (12/20) | 10.03 s
[Task 15/25] Current/Best: 19.65/ 19.65 GFLOPS | Progress: (16/20) | 13.38 s
[Task 15/25] Current/Best: 10.28/ 19.65 GFLOPS | Progress: (20/20) | 17.27 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 10.24/ 18.11 GFLOPS | Progress: (4/20) | 5.76 s
[Task 16/25] Current/Best: 13.82/ 20.57 GFLOPS | Progress: (8/20) | 7.36 s
[Task 16/25] Current/Best: 6.58/ 20.57 GFLOPS | Progress: (12/20) | 9.36 s
[Task 16/25] Current/Best: 7.90/ 20.57 GFLOPS | Progress: (16/20) | 13.86 s
[Task 16/25] Current/Best: 14.50/ 20.57 GFLOPS | Progress: (20/20) | 17.05 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 7.63/ 12.68 GFLOPS | Progress: (4/20) | 4.83 s
[Task 17/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (8/20) | 8.06 s
[Task 17/25] Current/Best: 20.92/ 20.92 GFLOPS | Progress: (12/20) | 12.25 s
[Task 17/25] Current/Best: 12.30/ 20.92 GFLOPS | Progress: (16/20) | 14.64 s
[Task 17/25] Current/Best: 16.26/ 20.92 GFLOPS | Progress: (20/20) | 17.20 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 13.11/ 20.08 GFLOPS | Progress: (4/20) | 3.78 s
[Task 18/25] Current/Best: 18.25/ 20.35 GFLOPS | Progress: (8/20) | 5.58 s
[Task 18/25] Current/Best: 17.47/ 20.35 GFLOPS | Progress: (12/20) | 7.34 s
[Task 18/25] Current/Best: 12.91/ 20.35 GFLOPS | Progress: (16/20) | 9.52 s
[Task 18/25] Current/Best: 9.62/ 20.35 GFLOPS | Progress: (20/20) | 12.94 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 2.68/ 18.61 GFLOPS | Progress: (4/20) | 5.57 s
[Task 19/25] Current/Best: 17.89/ 18.61 GFLOPS | Progress: (8/20) | 9.49 s
[Task 19/25] Current/Best: 9.19/ 18.61 GFLOPS | Progress: (12/20) | 12.01 s
[Task 19/25] Current/Best: 1.55/ 18.61 GFLOPS | Progress: (16/20) | 16.91 s
[Task 19/25] Current/Best: 19.10/ 19.10 GFLOPS | Progress: (20/20) | 19.50 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 11.28/ 11.55 GFLOPS | Progress: (4/20) | 5.83 s
[Task 20/25] Current/Best: 13.86/ 14.85 GFLOPS | Progress: (8/20) | 8.22 s
[Task 20/25] Current/Best: 6.48/ 14.85 GFLOPS | Progress: (12/20) | 10.55 s
[Task 20/25] Current/Best: 13.68/ 17.78 GFLOPS | Progress: (16/20) | 14.01 s
[Task 20/25] Current/Best: 16.73/ 17.78 GFLOPS | Progress: (20/20) | 16.44 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 21/25] Current/Best: 16.95/ 16.95 GFLOPS | Progress: (4/20) | 4.15 s
[Task 21/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (8/20) | 7.14 s
[Task 21/25] Current/Best: 8.88/ 18.79 GFLOPS | Progress: (12/20) | 8.74 s
[Task 21/25] Current/Best: 2.70/ 18.79 GFLOPS | Progress: (16/20) | 11.14 s
[Task 21/25] Current/Best: 13.40/ 18.79 GFLOPS | Progress: (20/20) | 13.60 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 6.34/ 11.62 GFLOPS | Progress: (4/20) | 4.80 s
[Task 22/25] Current/Best: 8.00/ 16.25 GFLOPS | Progress: (8/20) | 7.47 s
[Task 22/25] Current/Best: 7.97/ 17.98 GFLOPS | Progress: (12/20) | 10.11 s
[Task 22/25] Current/Best: 7.94/ 17.98 GFLOPS | Progress: (16/20) | 12.27 s
[Task 22/25] Current/Best: 4.54/ 20.67 GFLOPS | Progress: (20/20) | 17.21 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 19.90/ 19.91 GFLOPS | Progress: (4/20) | 4.25 s
[Task 23/25] Current/Best: 5.34/ 19.91 GFLOPS | Progress: (8/20) | 6.80 s
[Task 23/25] Current/Best: 6.11/ 19.91 GFLOPS | Progress: (12/20) | 9.65 s
[Task 23/25] Current/Best: 13.13/ 22.90 GFLOPS | Progress: (16/20) | 13.23 s
[Task 23/25] Current/Best: 19.34/ 22.90 GFLOPS | Progress: (20/20) | 16.45 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (4/20) | 11.85 s
[Task 24/25] Current/Best: 3.57/ 7.40 GFLOPS | Progress: (8/20) | 23.99 s
[Task 24/25] Current/Best: 9.64/ 9.64 GFLOPS | Progress: (12/20) | 34.93 s Done.
+
[Task 24/25] Current/Best: 2.29/ 10.71 GFLOPS | Progress: (16/20) | 45.88 s
[Task 24/25] Current/Best: 6.94/ 10.71 GFLOPS | Progress: (20/20) | 56.83 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 8.94/ 9.24 GFLOPS | Progress: (4/20) | 13.85 s
[Task 25/25] Current/Best: 5.93/ 9.24 GFLOPS | Progress: (8/20) | 24.78 s
[Task 25/25] Current/Best: 6.26/ 9.24 GFLOPS | Progress: (12/20) | 29.32 s
[Task 25/25] Current/Best: 7.94/ 9.24 GFLOPS | Progress: (16/20) | 40.25 s
[Task 25/25] Current/Best: 5.92/ 9.24 GFLOPS | Progress: (20/20) | 51.19 s
@@ -731,8 +731,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 423.5480854100001, 'median': 423.5180550500104, 'std': 3.025069320486451}
- unoptimized: {'mean': 515.7709692800006, 'median': 515.0009511999997, 'std': 2.2209522109315}
+ optimized: {'mean': 412.4336003600001, 'median': 412.09299079999937, 'std': 1.9291336960928867}
+ unoptimized: {'mean': 512.1992977499997, 'median': 511.0846481500005, 'std': 2.718325039446462}
@@ -755,7 +755,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 6.435 seconds)
+ **Total running time of the script:** ( 11 minutes 33.016 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 de62a5b39c..83323c75d9 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -270,7 +270,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.242e-07 secs/op
+ 1.287e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 50d1d14649..2253d02340 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -260,7 +260,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x2375ffe0)), stage(b, placeholder(b, 0x20d0b990)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x2187dbd0)), stage(b, placeholder(b, 0x4b5c8e0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 2899c6952d..5dab9d7b4b 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
Computation times
=================
-**15:31.930** total execution time for **tutorial** files:
+**14:49.341** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:06.435 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:33.016 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:29.595 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:16.697 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.401 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.150 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.379 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:33.483 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:18.618 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.711 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.464 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:03.295 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.845 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.818 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.180 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.162 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.008 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index becce2470f..ac510fc44f 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -294,7 +294,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000007
@@ -393,7 +393,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000008
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.922929999040207e-06 1.0
- naive 6.755800000000001e-06 0.8526895985220627
- parallel 6.9898e-06 0.8822241267872811
- vector 2.45943e-05 3.104192515013938
+ numpy 6.807869999647664e-06 1.0
+ naive 6.9094e-06 1.0149136220811488
+ parallel 8.2734e-06 1.2152699743720403
+ vector 2.46488e-05 3.6206331791405653
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018479
+ Numpy running time: 0.018272
@@ -981,7 +981,7 @@ optimizations.
.. code-block:: none
- none: 3.342083
+ none: 3.205106
@@ -1083,7 +1083,7 @@ schedule.
.. code-block:: none
- blocking: 0.312642
+ blocking: 0.296652
@@ -1178,7 +1178,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.348580
+ vectorization: 0.332271
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1251,7 +1251,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116981
+ loop permutation: 0.115928
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1349,7 +1349,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108607
+ array packing: 0.108467
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1441,7 +1441,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111039
+ block caching: 0.110566
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1526,7 +1526,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146690
+ parallelization: 0.145482
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1606,13 +1606,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3420834258 1.0
- blocking 0.3126420623 0.09354705507543169
- vectorization 0.3485796604 0.10430010744467276
- loop permutation 0.11698097410000001 0.03500240993295914
- array packing 0.1086071926 0.03249685264035637
- block caching 0.11103898990000001 0.033224481783670747
- parallelization 0.1466900011 0.04389178318159026
+ none 3.20510635 1.0
+ blocking 0.2966517709 0.09255598364154126
+ vectorization 0.3322708254 0.10366920442437114
+ loop permutation 0.11592775500000001 0.0361697061939926
+ array packing 0.10846665370000001 0.03384182671504801
+ block caching 0.1105661145 0.034496862951209094
+ parallelization 0.1454820974 0.045390723899068126
@@ -1652,11 +1652,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 0.401 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 06d75e79d6..65dc604f13 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-aec46dc0929835b2d47eefff924bc754a9727096
+bf0607bd317a7db8eba1a91c12170934c1ad201f
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index dc0b1f1576..96093b79e5 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.639 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.545 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index 0695dd3f27..23602761c1 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ pip install -U tensorflow --user
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 969ms/step
+1/1 [==============================] - 1s 937ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 02a476c195..fc73368f2e 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -440,7 +440,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf79b09cf-0b43-4d0e-a19e-72a9d1e9a937 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.zipf91ff55f-ac6c-4063-9162-858a3678bd8d 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 da81e2fad2..e45aaaae84 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -448,12 +448,12 @@ 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, 67.3MB/s]
- 39%|###8 | 16.0M/41.5M [00:00<00:00, 48.9MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 52.1MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 59.1MB/s]
- 96%|#########6| 40.0M/41.5M [00:00<00:00, 62.8MB/s]
-100%|##########| 41.5M/41.5M [00:00<00:00, 60.9MB/s]
+ 19%|#9 | 8.03M/41.5M [00:00<00:00, 84.2MB/s]
+ 39%|###8 | 16.1M/41.5M [00:00<00:00, 38.2MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 49.0MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 57.4MB/s]
+ 93%|#########2| 38.5M/41.5M [00:00<00:00, 56.0MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 54.1MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 76555d4523..7bed27f6ad 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -431,10 +431,11 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 32%|###2 | 14.3M/44.7M [00:00<00:00, 143MB/s]
- 63%|######2 | 27.9M/44.7M [00:00<00:00, 109MB/s]
- 87%|########6 | 38.7M/44.7M [00:00<00:00, 110MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 105MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 66.2MB/s]
+ 49%|####9 | 22.0M/44.7M [00:00<00:00, 109MB/s]
+ 74%|#######3 | 32.9M/44.7M [00:00<00:00, 80.7MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 94.1MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 91.1MB/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 dec84d57ef..31b5099855 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -645,7 +645,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.071 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.810 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 1c090eaaca..0eaf157551 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:51.751</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:37.514</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_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>01:15.071</p></td>
+<td><p>01:10.810</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>01:11.639</p></td>
+<td><p>01:08.545</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>00:48.431</p></td>
+<td><p>00:45.698</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:32.706</p></td>
+<td><p>00:31.767</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:29.597</p></td>
+<td><p>00:28.497</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:27.125</p></td>
+<td><p>00:25.793</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:25.035</p></td>
+<td><p>00:25.143</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:22.845</p></td>
+<td><p>00:22.333</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:16.845</p></td>
+<td><p>00:16.515</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>00:02.457</p></td>
+<td><p>00:02.413</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 7ec8673593..1362957cd5 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -919,7 +919,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2806.9997 2807.6032 2811.0758 2803.7583 2.1930
+ 2755.6715 2754.1031 2767.5189 2751.3624 4.3784
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
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 61c5622895..2ca4dd67f0 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -661,7 +661,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4209 16.4410 16.7418 16.0910 0.2278
+ 16.1268 15.7303 19.0033 15.4902 1.0054
</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 60f50c27d5..6be2dff68a 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -453,22 +453,26 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 9%|9 | 15.6M/170M [00:00<00:00, 164MB/s]
- 18%|#8 | 31.3M/170M [00:00<00:01, 104MB/s]
- 25%|##4 | 42.4M/170M [00:00<00:01, 95.7MB/s]
- 31%|### | 52.1M/170M [00:00<00:01, 94.5MB/s]
- 36%|###6 | 61.4M/170M [00:00<00:01, 93.2MB/s]
- 42%|####2 | 72.0M/170M [00:00<00:01, 86.1MB/s]
- 47%|####7 | 80.4M/170M [00:00<00:01, 70.9MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 69.9MB/s]
- 58%|#####8 | 98.7M/170M [00:01<00:00, 80.3MB/s]
- 66%|######5 | 112M/170M [00:01<00:00, 88.6MB/s]
- 74%|#######4 | 126M/170M [00:01<00:00, 104MB/s]
- 80%|######## | 137M/170M [00:01<00:00, 87.4MB/s]
- 86%|########5 | 146M/170M [00:01<00:00, 84.0MB/s]
- 91%|#########1| 155M/170M [00:01<00:00, 88.5MB/s]
- 99%|#########8| 168M/170M [00:01<00:00, 99.6MB/s]
-100%|##########| 170M/170M [00:01<00:00, 91.3MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 58.4MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 59.6MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:02, 67.7MB/s]
+ 18%|#8 | 30.6M/170M [00:00<00:02, 62.4MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:02, 62.7MB/s]
+ 29%|##8 | 49.1M/170M [00:00<00:01, 71.6MB/s]
+ 33%|###3 | 56.1M/170M [00:00<00:01, 69.2MB/s]
+ 38%|###7 | 64.0M/170M [00:00<00:01, 71.6MB/s]
+ 43%|####3 | 73.1M/170M [00:01<00:01, 78.4MB/s]
+ 48%|####7 | 80.8M/170M [00:01<00:01, 60.1MB/s]
+ 52%|#####1 | 88.0M/170M [00:01<00:01, 58.6MB/s]
+ 57%|#####6 | 96.0M/170M [00:01<00:01, 58.4MB/s]
+ 61%|######1 | 104M/170M [00:01<00:01, 60.9MB/s]
+ 69%|######9 | 118M/170M [00:01<00:00, 81.0MB/s]
+ 75%|#######5 | 128M/170M [00:01<00:00, 82.6MB/s]
+ 80%|######## | 136M/170M [00:02<00:00, 74.3MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 75.9MB/s]
+ 93%|#########2| 158M/170M [00:02<00:00, 92.8MB/s]
+ 98%|#########8| 167M/170M [00:02<00:00, 56.1MB/s]
+100%|##########| 170M/170M [00:02<00:00, 66.2MB/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=& [...]
@@ -566,7 +570,7 @@ 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 12.631 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 11.699 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 0a4a4d23f8..68b074aa54 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -497,8 +497,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 64.9MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 57.3MB/s]
+ 60%|#####9 | 8.12M/13.6M [00:00<00:00, 74.6MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 86.9MB/s]
</pre></div>
</div>
</div>
@@ -589,7 +589,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3247 90.2200 91.9962 90.0500 0.2935
+ 90.5344 90.4058 94.1261 90.0283 0.7032
</pre></div>
</div>
<div class="admonition note">
@@ -628,7 +628,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.540 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.287 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 97165d54d4..b5bc58a06d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -582,7 +582,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.5761 119.5501 120.5232 118.6987 0.3760
+ 119.2738 119.2231 121.0559 117.5871 0.5324
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +610,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 30.015 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 26.963 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 3750f46b82..81fb416fae 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -520,7 +520,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.861 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.751 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 7cf332ba3e..72b884436a 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -462,22 +462,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6358/132723 [00:00<00:01, 63552.03KB/s]
- 11%|#1 | 14950/132723 [00:00<00:01, 76699.68KB/s]
- 17%|#7 | 22621/132723 [00:00<00:01, 67068.57KB/s]
- 24%|##3 | 31237/132723 [00:00<00:01, 74000.15KB/s]
- 30%|##9 | 39745/132723 [00:00<00:01, 77775.85KB/s]
- 36%|###6 | 48353/132723 [00:00<00:01, 80496.74KB/s]
- 43%|####2 | 56484/132723 [00:00<00:01, 74310.50KB/s]
- 49%|####8 | 65025/132723 [00:00<00:00, 77588.33KB/s]
- 55%|#####5 | 73620/132723 [00:00<00:00, 80067.31KB/s]
- 62%|######1 | 82230/132723 [00:01<00:00, 81862.25KB/s]
- 68%|######8 | 90487/132723 [00:01<00:00, 75469.36KB/s]
- 75%|#######4 | 99090/132723 [00:01<00:00, 78441.69KB/s]
- 81%|########1 | 107725/132723 [00:01<00:00, 80706.55KB/s]
- 88%|########7 | 116333/132723 [00:01<00:00, 82266.50KB/s]
- 94%|#########4| 124973/132723 [00:01<00:00, 83474.44KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 79005.53KB/s]
+ 4%|4 | 5946/132723 [00:00<00:02, 59456.51KB/s]
+ 10%|# | 13803/132723 [00:00<00:01, 70695.64KB/s]
+ 16%|#6 | 21655/132723 [00:00<00:01, 74266.67KB/s]
+ 22%|##2 | 29474/132723 [00:00<00:01, 75812.53KB/s]
+ 28%|##8 | 37330/132723 [00:00<00:01, 76801.81KB/s]
+ 34%|###3 | 45073/132723 [00:00<00:01, 77012.85KB/s]
+ 40%|###9 | 52829/132723 [00:00<00:01, 77188.25KB/s]
+ 46%|####5 | 60677/132723 [00:00<00:00, 77595.42KB/s]
+ 52%|#####1 | 68536/132723 [00:00<00:00, 77905.12KB/s]
+ 58%|#####7 | 76355/132723 [00:01<00:00, 77992.16KB/s]
+ 63%|######3 | 84220/132723 [00:01<00:00, 78188.26KB/s]
+ 69%|######9 | 92039/132723 [00:01<00:00, 78120.94KB/s]
+ 75%|#######5 | 99852/132723 [00:01<00:00, 78084.82KB/s]
+ 81%|########1 | 107661/132723 [00:01<00:00, 77891.75KB/s]
+ 87%|########7 | 115486/132723 [00:01<00:00, 77997.78KB/s]
+ 93%|#########2| 123320/132723 [00:01<00:00, 78093.70KB/s]
+ 99%|#########8| 131130/132723 [00:01<00:00, 78046.60KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 77075.80KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -516,7 +518,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 11.798 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 3.244 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 fce51e9931..263d9c9732 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:48.577</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>13:35.475</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:12.631</p></td>
+<td><p>03:11.699</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:11.798</p></td>
+<td><p>03:03.244</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>02:30.015</p></td>
+<td><p>02:26.963</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>01:23.861</p></td>
+<td><p>01:29.751</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>01:07.540</p></td>
+<td><p>01:05.287</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>00:55.236</p></td>
+<td><p>00:53.720</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:36.651</p></td>
+<td><p>00:34.792</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:25.913</p></td>
+<td><p>00:25.095</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:24.925</p></td>
+<td><p>00:24.917</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 7cac24a817..1011aba092 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -621,7 +621,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip76ded8db-3ddc-4079-a899-ee22f9540099 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.zip932c3960-6925-42b9-a6dc-715b267d6e4b 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 9c5da8b2b6..a294c3ef54 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:49.492</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:46.738</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:45.767</p></td>
+<td><p>00:43.336</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>00:02.600</p></td>
+<td><p>00:02.385</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>00:01.117</p></td>
+<td><p>00:01.010</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index d632b7492f..7146b50ea9 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -525,10 +525,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7700us [7700us] (46.47%; 46.47%)
-FoldScaleAxis: 8870us [9us] (53.53%; 53.53%)
- FoldConstant: 8862us [1749us] (53.48%; 99.90%)
- InferType: 7113us [7113us] (42.93%; 80.27%)
+InferType: 7220us [7220us] (46.63%; 46.63%)
+FoldScaleAxis: 8262us [7us] (53.37%; 53.37%)
+ FoldConstant: 8256us [1691us] (53.32%; 99.92%)
+ InferType: 6564us [6564us] (42.40%; 79.51%)
</pre></div>
</div>
</div>
@@ -550,10 +550,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7342us [7342us] (44.98%; 44.98%)
-FoldScaleAxis: 8980us [8us] (55.02%; 55.02%)
- FoldConstant: 8972us [1878us] (54.97%; 99.91%)
- InferType: 7094us [7094us] (43.46%; 79.07%)
+InferType: 6583us [6583us] (45.02%; 45.02%)
+FoldScaleAxis: 8040us [4us] (54.98%; 54.98%)
+ FoldConstant: 8036us [1665us] (54.95%; 99.95%)
+ InferType: 6371us [6371us] (43.57%; 79.28%)
</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 675bda3fbb..74adf21c36 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -577,7 +577,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 35.912033 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.155872 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 4062ce3b60..6793cd839f 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -914,7 +914,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.184669 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.336589 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 271fca866b..7eca0e1971 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -474,8 +474,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017942
-Baseline: 3.372778
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017974
+Baseline: 3.206709
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -534,7 +534,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.322392
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300285
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -600,7 +600,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.335350
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.328322
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -660,7 +660,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.123002
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114948
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -742,7 +742,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109568
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109372
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -827,7 +827,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111175
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111690
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -916,7 +916,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.149820
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146278
</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 3112941e60..de14dd40e3 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.298</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.109</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.558</p></td>
+<td><p>00:31.510</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>00:01.600</p></td>
+<td><p>00:01.542</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>00:01.139</p></td>
+<td><p>00:01.057</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 b2b54d09dd..b3ad4db51e 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:23.581</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:11.353</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:41.707</p></td>
+<td><p>05:45.315</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>01:33.935</p></td>
+<td><p>01:31.063</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>01:02.919</p></td>
+<td><p>01:01.136</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>00:40.896</p></td>
+<td><p>00:30.982</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:12.379</p></td>
+<td><p>00:11.852</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:11.745</p></td>
+<td><p>00:11.006</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 7f70d276e3..f1ca33a5ba 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
@@ -503,49 +503,238 @@ cooperative fetching, unrolling and operator fusion.</p>
bias: Buffer(bias_2: Pointer(float32), float32, [1, 512, 1, 1], []),
compute: Buffer(compute_2: Pointer(float32), float32, [1, 512, 7, 7], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 8;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- for (xx.inner.init: int32, 0, 7) {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[xx.inner.init] = 0f32
- conv2d_nchw_1[(xx.inner.init + 7)] = 0f32
- }
- for (rc.outer.outer: int32, 0, 64) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 3) {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*28) + floordiv(threadIdx.x_1, 8)) < 81), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_1)] = @tir.if_then_else(((((9 <= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*62) + threadIdx.x_1), 81)) && (floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*62) + threadIdx.x_1), 81) < 72)) && (1 <= floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*8) + threadIdx.x_1), 9)) [...]
- }
- }
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1: int32, 0, 4) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 6) {
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 32)) < 24), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*1344) + (threadIdx.x_2*6)) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*294912) + (floordiv(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*56) + floordiv(threadIdx.x_2, 4)), 3)*4608)) + (rc.outer.outer*72)) + (floormod((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1* [...]
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [6144]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ for (rc.outer.outer: int32, 0, 8) {
+ for (rx.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*3136)
+ let cse_var_1: int32 = (rc.outer.outer*576)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3: Buffer(data_2, float32, [25088], [])[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(thread [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 1364)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2744), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 2940)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 2940), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3136), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 3332)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3332), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 2736)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1[(threadIdx.x_1 + 3724)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3724), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data_3[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 3920), 63)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadI [...]
}
- }
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (rx.outer.inner: int32, 0, 3) {
- for (rc.inner: int32, 0, 2) {
- for (ry.inner: int32, 0, 3) {
- for (xx.inner: int32, 0, 7) {
- let cse_var_1: int32 = (xx.inner + 7)
- {
- conv2d_nchw_1[xx.inner] = (conv2d_nchw_1[xx.inner] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.inner) + rx.outer.inner)]*kernel.shared_1[(((((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_1] = (conv2d_nchw_1[cse_var_1] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (rc.inner*81)) + (ry.inner*9)) + (floormod(threadIdx.x, 7)*9)) + xx.inner) + rx.outer.inner)]*kernel.shared_1[((((((floordiv(threadIdx.x, 7)*72) + (rc.outer.inner*18)) + (rc.inner*9)) + (ry.inner*3)) + rx.outer.inner) + 2304)]))
- }
- }
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[threadIdx.x_2] = kernel_3: Buffer(kernel_2, float32, [2359296], [])[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 196), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 4), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 392), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 588), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 784), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 980), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 20), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1176), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1372), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 28), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1568), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1764), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 12), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 1960), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2156), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 44), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2352), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2548), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2744), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 2940), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 20), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3136), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3332), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 68), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3528), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3724), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 76), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 3920), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 80), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4116), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 28), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4312), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 88), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4508), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 92), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4704), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 32), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 4900)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 4900), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 100), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5096)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5096), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5292)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5292), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 36), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5488)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5488), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 192), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5684)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5684), 192)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 192), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 5880)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 5880), 192)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 40), 64)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 68), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 6076)] = kernel_3[((((((blockIdx.x*147456) + (floordiv((threadIdx.x_2 + 6076), 192)*4608)) + cse_var_1) + (floordiv((threadIdx.x_2 + 124), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ }
+ for (rc.outer.inner: int32, 0, 16) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3072)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 192)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3264)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3073)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 193)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3265)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3074)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 194)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3266)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3075)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 195)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3267)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3076)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 196)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3268)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3077)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 197)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3269)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3078)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 198)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3270)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3079)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 199)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3271)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3080)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 200)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3272)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3081)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 201)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3273)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3082)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 202)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3274)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3083)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 203)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3275)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 384)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3456)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 576)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*252) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3648)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 385)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3457)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 577)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3649)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 386)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3458)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 578)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3650)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 387)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3459)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 579)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3651)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 388)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3460)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 580)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3652)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 389)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3461)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 581)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3653)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 390)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3462)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 582)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3654)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 391)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3463)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 583)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3655)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 392)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3464)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 584)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3656)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 393)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3465)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 585)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3657)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 394)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3466)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 586)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3658)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 395)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3467)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 587)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*252) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*12)) + 3659)]))
}
}
}
}
- for (i3.inner: int32, 0, 7) {
- compute_3: Buffer(compute_2, float32, [25088], [])[(((blockIdx.x*3136) + (threadIdx.x*7)) + i3.inner)] = max((conv2d_nchw_1[i3.inner] + bias_3: Buffer(bias_2, float32, [512], [])[((blockIdx.x*64) + floordiv(threadIdx.x, 7))]), 0f32)
- compute_3[((((blockIdx.x*3136) + (threadIdx.x*7)) + i3.inner) + 1568)] = max((conv2d_nchw_1[(i3.inner + 7)] + bias_3[(((blockIdx.x*64) + floordiv(threadIdx.x, 7)) + 32)]), 0f32)
+ for (i1.inner: int32, 0, 4) {
+ compute_3: Buffer(compute_2, float32, [25088], [])[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias_3: Buffer(bias_2, float32, [512], [])[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ compute_3[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias_3[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 16)]), 0f32)
}
}
}
@@ -582,7 +771,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.372 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.363 ms
</pre></div>
</div>
</div>
@@ -611,36 +800,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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=4)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
+conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+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=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -658,16 +847,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=6)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -685,45 +874,182 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[4608];
- for (int xx_inner_init = 0; xx_inner_init < 7; ++xx_inner_init) {
- conv2d_nchw[xx_inner_init] = 0.000000e+00f;
- conv2d_nchw[(xx_inner_init + 7)] = 0.000000e+00f;
- }
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 3; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 28) + (((int)threadIdx.x) >> 3)) < 81) {
- pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x))] = (((((9 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62) + ((int)threadIdx.x)) % 81)) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 62) + ((int)threadIdx.x)) % 81) < 72)) && (1 <= (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx.x)) % 9))) && ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 8) + ((int)threadIdx [...]
+extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[6144];
+ 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[7] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 196) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 588) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 980) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1372) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 1364)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2156) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2548)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2548) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2940)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2940) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3332)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3332) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3528)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 2736)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3724)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3724) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 112) {
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
}
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 < 4; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1) {
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 6; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 7) + (((int)threadIdx.x) >> 5)) < 24) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 1344) + (((int)threadIdx.x) * 6)) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = kernel[(((((((int)blockIdx.x) * 294912) + ((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 56) + (((int)threadIdx.x) >> 2)) / 3) * 4608)) + (rc_outer_outer * 72)) + (((((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer_1 * 448) + (((int)threadIdx.x) * 2)) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s / 3)) % 24) * 3)) + (ax0 [...]
- }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 4) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 8) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 4) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 16) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 20) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 8) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 28) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 32) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 12) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 40) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 44) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 16) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 52) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 56) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 20) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 64) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3332) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 68) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3528) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 24) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3724) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 76) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 80) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4116) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 28) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4312) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 88) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4508) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 92) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4704) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 4900)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4900) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 100) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5096)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5096) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 104) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5292)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5292) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 36) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5488)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5488) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5684)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5684) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 116) % 192) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 5880)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5880) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 40) & 63) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 68) {
+ kernel_shared[(((int)threadIdx.x) + 6076)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 6076) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 124) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
}
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int rc_inner = 0; rc_inner < 2; ++rc_inner) {
- for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
- for (int xx_inner = 0; xx_inner < 7; ++xx_inner) {
- conv2d_nchw[xx_inner] = (conv2d_nchw[xx_inner] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_inner) + rx_outer_inner)] * kernel_shared[((((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[(xx_inner + 7)] = (conv2d_nchw[(xx_inner + 7)] + (pad_temp_shared[((((((rc_outer_inner * 162) + (rc_inner * 81)) + (ry_inner * 9)) + ((((int)threadIdx.x) % 7) * 9)) + xx_inner) + rx_outer_inner)] * kernel_shared[(((((((((int)threadIdx.x) / 7) * 72) + (rc_outer_inner * 18)) + (rc_inner * 9)) + (ry_inner * 3)) + rx_outer_inner) + 2304)]));
- }
- }
- }
+ __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 * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3072)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 192)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3264)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3073)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 193)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3265)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3074)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 194)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3266)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3075)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 195)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3267)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3076)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 196)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3268)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3077)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 197)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3269)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3078)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 198)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3270)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3079)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 199)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3271)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3080)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 200)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3272)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3081)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 201)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3273)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3082)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 202)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3274)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3083)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 203)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3275)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 384)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3456)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 576)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 252) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3648)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 385)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3457)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 577)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3649)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 386)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3458)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 578)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3650)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 387)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3459)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 579)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3651)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 388)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3460)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 580)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3652)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 389)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3461)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 581)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3653)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 390)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3462)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 582)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3654)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 391)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3463)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 583)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3655)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 392)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3464)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 584)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3656)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 393)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3465)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 585)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3657)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 394)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3466)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 586)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3658)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 395)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3467)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 587)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 252) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 12)) + 3659)]));
}
}
}
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[(((((int)blockIdx.x) * 3136) + (((int)threadIdx.x) * 7)) + i3_inner)] = max((conv2d_nchw[i3_inner] + bias[((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 3136) + (((int)threadIdx.x) * 7)) + i3_inner) + 1568)] = max((conv2d_nchw[(i3_inner + 7)] + bias[(((((int)blockIdx.x) * 64) + (((int)threadIdx.x) / 7)) + 32)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 16)]), 0.000000e+00f);
}
}
</pre></div>
@@ -760,7 +1086,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 41.707 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 45.315 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 46d3d6c8dc..f72d52ed3f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -915,7 +915,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8856 7.8856 7.8875 7.8839 0.0015
+ 7.8911 7.8909 7.8937 7.8885 0.0021
</pre></div>
</div>
</div>
@@ -937,7 +937,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.919 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.136 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 8caffca4c7..cd7156e7e9 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -934,7 +934,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 768.8948 768.5418 772.1388 766.0039 2.5170
+ 748.8933 748.5468 749.8692 748.2639 0.6997
</pre></div>
</div>
</div>
@@ -956,7 +956,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.935 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.063 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 3b61b2acae..6a138ec488 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,27 +632,32 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [128, 512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [128, 512], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.inner.init: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [512], [])[((i.inner.init*16) + j.init)] = 0f32
- }
- }
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
- for (i.inner: int32, 0, 32) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_15[(cse_var_2 + 1)] - placeholder_15[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = ((i.inner*16) + j)
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_2] + elem_idx)])], 0f32)))
+ for (i0.outer: int32, 0, 4) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [1024], [])[((((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
+ }
+ }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_15: Buffer(placeholder_13, int32, [33], [])[(cse_var_1 + 1)] - placeholder_15[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_16: Buffer(placeholder_11, float32, [78656], [])[(((placeholder_15[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder_17: Buffer(placeholder_10, float32, [32768], [])[((((i0.outer*8192) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_18: Buffer(placeholder_12, int32, [4916], [])[(placeholder_15[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
}
for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute_5: Buffer(compute_2, float32, [65536], [])[ramp(cse_var_4, 1, 16)] = max((compute_4[ramp((i0.inner*16), 1, 16)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32)) + i1.inner)
+ compute_5: Buffer(compute_2, float32, [65536], [])[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_19: Buffer(placeholder_14, float32, [65536], [])[cse_var_4]), 0f32)
+ }
}
}
}
@@ -690,7 +695,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.665 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.698 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 a1d2753069..b6a6e71d28 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:47.003</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:49.273</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,22 +349,22 @@
</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>00:46.966</p></td>
+<td><p>00:49.238</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.022</p></td>
+<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 85e25e230d..bdbe83d7c6 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -567,8 +567,7 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 44.48/44.48 result: MeasureResult(costs=(0.005204324333333333,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.942298650741577, timestamp=1672879982.3740249) [('tile_f', [-1, 4, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9387861
-No: 2 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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
@@ -690,8 +689,8 @@ 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3905470
-No: 3 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5188327
+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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -813,8 +812,8 @@ 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, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9864484
-No: 4 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4397165
+No: 3 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -936,8 +935,8 @@ 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, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7637503
-No: 5 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9055567
+No: 4 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1059,8 +1058,8 @@ 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, 2, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1909563
-No: 6 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4972076
+No: 5 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1182,10 +1181,8 @@ 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, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8986874
-No: 7 GFLOPS: 26.75/44.48 result: MeasureResult(costs=(0.00865332025,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.840994358062744, timestamp=1672879990.439722) [('tile_f', [-1, 8, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3141163
-No: 8 GFLOPS: 28.72/44.48 result: MeasureResult(costs=(0.008059667692307692,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2247412204742432, timestamp=1672879991.2185087) [('tile_f', [-1, 1, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5495480
-No: 9 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8385233
+No: 6 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)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1307,8 +1304,9 @@ 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, 2, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1081533
-No: 10 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3731290
+No: 7 GFLOPS: 1.80/1.80 result: MeasureResult(costs=(0.1288972625,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.4602324962615967, timestamp=1672882308.158129) [('tile_f', [-1, 32, 2, 4]), ('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', 0), ('unroll_explicit', 0)],None,389293
+No: 8 GFLOPS: 0.00/1.80 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
@@ -1430,27 +1428,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 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, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2497385
-No: 11 GFLOPS: 8.19/44.48 result: MeasureResult(costs=(0.0282496565,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.6270527839660645, timestamp=1672880002.2008271) [('tile_f', [-1, 4, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8881246
-No: 12 GFLOPS: 0.00/44.48 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, 4, 2, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9996030
-No: 13 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3019588
+No: 9 GFLOPS: 0.00/1.80 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
@@ -1572,8 +1551,162 @@ 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, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2127140
-No: 14 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3480006
+No: 10 GFLOPS: 0.00/1.80 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 357, in evaluator
+ blob = feval(*args)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 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 171, in get_function
+ self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
+ File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
+ raise get_last_ffi_error()
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 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: 0x00007f5da4569fa2
+ 11: _ctypes_callproc
+ 10: ffi_call
+ 9: ffi_call_unix64
+ 8: TVMModGetFunction
+ at ../src/runtime/c_runtime_api.cc:408
+ 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
+ at ../src/runtime/module.cc:66
+ 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
+ at ../src/runtime/rpc/rpc_module.cc:185
+ 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.cc:1007
+ 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
+ at ../src/runtime/rpc/rpc_endpoint.h:223
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ at ../include/tvm/runtime/packed_func.h:1617
+ 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, 8, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,676998
+No: 11 GFLOPS: 219.15/219.15 result: MeasureResult(costs=(0.0010563536736842105,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8245925903320312, timestamp=1672882323.4235377) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3955680
+No: 12 GFLOPS: 0.00/219.15 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
@@ -1695,8 +1828,8 @@ 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, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1659133
-No: 15 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9971620
+No: 13 GFLOPS: 0.00/219.15 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
@@ -1818,8 +1951,8 @@ 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, 128, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8096227
-No: 16 GFLOPS: 0.00/44.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5509336
+No: 14 GFLOPS: 0.00/219.15 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
@@ -1941,161 +2074,395 @@ 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, 256, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7727563
-No: 17 GFLOPS: 0.00/44.48 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 357, in evaluator
- blob = feval(*args)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3321061
+No: 15 GFLOPS: 0.00/219.15 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_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
- File "tvm/_ffi/_cython/./packed_func.pxi", line 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/./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):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 23: 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:
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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):
- 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 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
+ 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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, 32, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5981585
+No: 16 GFLOPS: 0.00/219.15 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_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 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: 0x00007f5b5d5c6fa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
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
+ 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):
- 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, 4, 1, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2259318
-No: 18 GFLOPS: 0.00/44.48 result: 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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, 32, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9402657
+No: 17 GFLOPS: 0.00/219.15 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_host=task.target_host, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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:1730
+ 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:1670
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1630
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1645
+ 13: operator()
+ at ../src/driver/driver_api.cc:394
+ 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:380
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:275
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:453
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1749
+ 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:1693
+ 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:1617
+ 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, 16, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1574204
+No: 18 GFLOPS: 0.00/219.15 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, 64, 2, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9297490
+No: 19 GFLOPS: 0.00/219.15 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
@@ -2217,9 +2584,8 @@ 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, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6114857
-No: 19 GFLOPS: 235.08/235.08 result: MeasureResult(costs=(0.0009847759333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3667175769805908, timestamp=1672880011.0845015) [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3531310
-No: 20 GFLOPS: 0.00/235.08 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 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,6834654
+No: 20 GFLOPS: 0.00/219.15 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
@@ -2341,7 +2707,7 @@ 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, 32, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3656909
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,342716
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2380,9 +2746,9 @@ 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, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3531310
+[('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3955680
Finish loading 20 records
-Time cost of this operator: 0.001410
+Time cost of this operator: 0.001515
</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 7502a4f437..15013eede1 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -598,10 +598,10 @@ 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 312.5 98.708 (1, 2, 10, 10, 3) 2 1 [312.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.111 0.983 (1, 6, 10, 10) 1 1 [3.111]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.981 0.31 (1, 1, 10, 10, 3) 1 1 [0.981]
-Total_time - 316.592 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.2 98.73 (1, 2, 10, 10, 3) 2 1 [311.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.958 (1, 6, 10, 10) 1 1 [3.021]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.982 0.312 (1, 1, 10, 10, 3) 1 1 [0.982]
+Total_time - 315.203 - - - - -
</pre></div>
</div>
</div>
@@ -653,10 +653,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.3 97.289 (1, 6, 10, 10, 1) 2 1 [100.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.81 1.756 (1, 6, 10, 10) 1 1 [1.81]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.984 0.955 (1, 1, 10, 10, 3) 1 1 [0.984]
-Total_time - 103.095 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 115.4 97.768 (1, 6, 10, 10, 1) 2 1 [115.4]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.784 1.512 (1, 6, 10, 10) 1 1 [1.784]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.851 0.721 (1, 3, 10, 10, 1) 1 1 [0.851]
+Total_time - 118.035 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 952c0dc292..6cc74430e6 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -440,8 +440,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
- 61%|###### | 2.09M/3.42M [00:00<00:00, 16.7MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 25.1MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 80.9MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -565,7 +564,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.460 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.876 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 db2224a01e..0edb5f49a6 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -530,7 +530,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpwftzjw4b/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp4jvlr05e/images/random'
</pre></div>
</div>
</div>
@@ -590,8 +590,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpwftzjw4b/images/target contains 8144 images
-/tmp/tmpwftzjw4b/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp4jvlr05e/images/target contains 8144 images
+/tmp/tmp4jvlr05e/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -703,13 +703,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2124 - accuracy: 0.9283 - val_loss: 0.1220 - val_accuracy: 0.9588 - 47s/epoch - 144ms/step
+328/328 - 47s - loss: 0.2343 - accuracy: 0.9174 - val_loss: 0.1764 - val_accuracy: 0.9449 - 47s/epoch - 142ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.0956 - accuracy: 0.9637 - val_loss: 0.1147 - val_accuracy: 0.9619 - 44s/epoch - 133ms/step
+328/328 - 44s - loss: 0.0970 - accuracy: 0.9649 - val_loss: 0.1839 - val_accuracy: 0.9422 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 44s - loss: 0.0630 - accuracy: 0.9763 - val_loss: 0.1039 - val_accuracy: 0.9653 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0676 - accuracy: 0.9743 - val_loss: 0.1062 - val_accuracy: 0.9619 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7fa0ab739610>
+<keras.callbacks.History object at 0x7f385773f990>
</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 18.778 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 21.101 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 d0a0e278cf..5aa915cd2d 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:31.986</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:25.205</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:18.778</p></td>
+<td><p>04:21.101</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:07.460</p></td>
+<td><p>01:01.876</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:53.517</p></td>
+<td><p>00:50.767</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.303</p></td>
+<td><p>00:07.693</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.926</p></td>
+<td><p>00:03.765</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index eeec0a8598..962e2a30a3 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.836</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.964</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.613</p></td>
+<td><p>00:32.081</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.588</p></td>
+<td><p>00:10.089</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>00:01.627</p></td>
+<td><p>00:01.787</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 82c6d51e98..0e55f3df6f 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fa0ab9584d0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f3851776170>
</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 afa7735e26..aee62d9fab 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:06.541</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.606</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.014</p></td>
+<td><p>00:05.144</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>00:01.167</p></td>
+<td><p>00:01.115</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>00:00.581</p></td>
+<td><p>00:00.579</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>00:00.564</p></td>
+<td><p>00:00.554</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>00:00.113</p></td>
+<td><p>00:00.112</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -373,7 +373,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.029</p></td>
+<td><p>00:00.028</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 872ec76cee..7927204d82 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [512, 64], []),
C: Buffer(C_2: Pointer(float32), float32, [1024, 512], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpvhov1_tz/input0.cc'\nsource_filename = \"/tmp/tmpvhov1_tz/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpwtgp1e3q/input0.cc'\nsource_filename = \"/tmp/tmpwtgp1e3q/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 23d2181e9d..1ef28de467 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,17 +229,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 43e4a00898..2402726ea7 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 044f9bbbbc..3e6941a419 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/aec46dc09/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 6cdd2cbb38..73d0532ea4 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/aec46dc09/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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 c01cf1a500..c2d6d9aba2 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/aec46dc09/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index eb7ac2093c..6b9f26d15d 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/aec46dc09/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index b127759fed..9c6ffc57f0 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/aec46dc09/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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 c96dcb66af..23f430c82f 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/aec46dc09/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index e963781bd0..f17c72590f 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 83d476024a..9570fd5c39 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 2af055dfc9..c169401ed0 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/aec46dc09/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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 e970c83881..dd66220dfb 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 1216f7597f..60c53c1045 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/aec46dc09/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 3155c7e55f..c42370f087 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 9e0f922a1f..d90abecc6f 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/aec46dc09/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 40cd7152da..fe91f71907 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/aec46dc09/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 7283ceaf09..aebc2da7a9 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/aec46dc09/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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 b48cb4f62a..5d1a0bdafa 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/aec46dc09/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 2afdd075c8..1204eacf26 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/aec46dc09/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 4a82d1b1aa..f4f10ad051 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/aec46dc09/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 470b11bc31..a23ae8e04a 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/aec46dc09/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index f105b5b73c..ef60dc2c23 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/aec46dc09/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 871b8a8e9b..8932715dce 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index e92fee3f57..2aa3d1bf7a 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/aec46dc09/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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 675003d4fc..897b52f8ad 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/aec46dc09/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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 781fd43850..c14d23ef16 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/aec46dc09/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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/aec46dc09/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/bf0607bd3/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 b9cb35d7ae..62e907349c 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 46b03e6d67..38015db51f 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:27.254</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:25.886</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:27.248</p></td>
+<td><p>00:25.880</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 399be6c9e1..23b3086131 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -582,7 +582,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 30.21s!
+resnet18_v1 inference graph built in 28.43s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 3d0227dcf0..79a815d86b 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -600,7 +600,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 20.47s!
+yolov3-tiny inference graph built in 19.28s!
</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 ae1f911938..e8450cd62d 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:42.356</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.206</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:52.085</p></td>
+<td><p>00:45.962</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:50.271</p></td>
+<td><p>00:45.244</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 80052d6e9c..4f41c4966d 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.211</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.182</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.737</p></td>
+<td><p>00:02.725</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>00:00.474</p></td>
+<td><p>00:00.458</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 c2e81631be..df1dee8c8d 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.852</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.800</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.456</p></td>
+<td><p>00:00.422</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>00:00.396</p></td>
+<td><p>00:00.379</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 d46ab09c7b..a8e2c5cf8f 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -491,9 +491,6 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.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>
@@ -580,7 +577,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.587 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 95.405 ms
</pre></div>
</div>
</div>
@@ -654,7 +651,7 @@ 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 29.595 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.697 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 195df2b6f3..4b871103e6 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -679,16 +679,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 12.62/12.62 result: MeasureResult(costs=(0.0212750562,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7127289772033691, timestamp=1672878546.5182264) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
-No: 2 GFLOPS: 3.28/12.62 result: MeasureResult(costs=(0.0818079904,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5599911212921143, timestamp=1672878548.0807588) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
-No: 3 GFLOPS: 2.83/12.62 result: MeasureResult(costs=(0.0947567186,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7626209259033203, timestamp=1672878550.6288085) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
-No: 4 GFLOPS: 9.69/12.62 result: MeasureResult(costs=(0.0276888212,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.8194856643676758, timestamp=1672878551.3305037) [('tile_y', [-1, 8]), ('tile_x', [-1, 128])],None,73
-No: 5 GFLOPS: 4.09/12.62 result: MeasureResult(costs=(0.0656034804,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3047773838043213, timestamp=1672878552.7669842) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
-No: 6 GFLOPS: 9.77/12.62 result: MeasureResult(costs=(0.0274755166,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7110121250152588, timestamp=1672878554.2572384) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
-No: 7 GFLOPS: 4.15/12.62 result: MeasureResult(costs=(0.0646942704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2955398559570312, timestamp=1672878556.3292017) [('tile_y', [-1, 16]), ('tile_x', [-1, 16])],None,44
-No: 8 GFLOPS: 2.22/12.62 result: MeasureResult(costs=(0.1209604482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1650946140289307, timestamp=1672878558.5155125) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
-No: 9 GFLOPS: 14.36/14.36 result: MeasureResult(costs=(0.0186932454,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5641310214996338, timestamp=1672878559.1960435) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
-No: 10 GFLOPS: 7.46/14.36 result: MeasureResult(costs=(0.035994663,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7751169204711914, timestamp=1672878560.0260532) [('tile_y', [-1, 1]), ('tile_x', [-1, 32])],None,50
+No: 1 GFLOPS: 12.40/12.40 result: MeasureResult(costs=(0.0216470044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6152174472808838, timestamp=1672880904.961685) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+No: 2 GFLOPS: 14.34/14.34 result: MeasureResult(costs=(0.0187140628,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6137557029724121, timestamp=1672880905.5090969) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
+No: 3 GFLOPS: 1.22/14.34 result: MeasureResult(costs=(0.2195632924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.7343947887420654, timestamp=1672880910.0190434) [('tile_y', [-1, 2]), ('tile_x', [-1, 1])],None,1
+No: 4 GFLOPS: 1.64/14.34 result: MeasureResult(costs=(0.16361529660000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.837488889694214, timestamp=1672880912.8840718) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 5 GFLOPS: 3.05/14.34 result: MeasureResult(costs=(0.08789075560000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6464266777038574, timestamp=1672880914.7544508) [('tile_y', [-1, 256]), ('tile_x', [-1, 8])],None,38
+No: 6 GFLOPS: 13.88/14.34 result: MeasureResult(costs=(0.0193371728,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5762917995452881, timestamp=1672880916.068992) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+No: 7 GFLOPS: 1.18/14.34 result: MeasureResult(costs=(0.227297203,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.9153645038604736, timestamp=1672880920.7527018) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+No: 8 GFLOPS: 12.80/14.34 result: MeasureResult(costs=(0.020963635799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6822052001953125, timestamp=1672880921.3441238) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+No: 9 GFLOPS: 2.82/14.34 result: MeasureResult(costs=(0.0950836638,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.727813959121704, timestamp=1672880923.186269) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+No: 10 GFLOPS: 11.37/14.34 result: MeasureResult(costs=(0.023602291,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5843014717102051, timestamp=1672880923.8179212) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
</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 2fb2d98642..fa993f7b81 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -560,7 +560,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 515.7709692800006, 'median': 515.0009511999997, 'std': 2.2209522109315}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 512.1992977499997, 'median': 511.0846481500005, 'std': 2.718325039446462}
</pre></div>
</div>
</div>
@@ -712,178 +712,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 9.24/ 22.32 GFLOPS | Progress: (4/20) | 7.75 s
-[Task 1/25] Current/Best: 11.26/ 22.32 GFLOPS | Progress: (8/20) | 10.85 s
-[Task 1/25] Current/Best: 13.52/ 22.32 GFLOPS | Progress: (12/20) | 13.63 s
-[Task 1/25] Current/Best: 23.55/ 23.55 GFLOPS | Progress: (16/20) | 17.19 s
-[Task 1/25] Current/Best: 14.41/ 23.55 GFLOPS | Progress: (20/20) | 20.13 s Done.
+[Task 1/25] Current/Best: 12.45/ 19.03 GFLOPS | Progress: (4/20) | 7.34 s
+[Task 1/25] Current/Best: 22.90/ 22.90 GFLOPS | Progress: (8/20) | 11.82 s
+[Task 1/25] Current/Best: 11.67/ 22.90 GFLOPS | Progress: (12/20) | 15.25 s
+[Task 1/25] Current/Best: 12.34/ 22.90 GFLOPS | Progress: (16/20) | 17.76 s
+[Task 1/25] Current/Best: 7.15/ 22.90 GFLOPS | Progress: (20/20) | 20.17 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 9.99/ 13.02 GFLOPS | Progress: (4/20) | 4.10 s
-[Task 2/25] Current/Best: 15.99/ 15.99 GFLOPS | Progress: (8/20) | 6.47 s
-[Task 2/25] Current/Best: 16.72/ 16.72 GFLOPS | Progress: (12/20) | 8.09 s
-[Task 2/25] Current/Best: 7.00/ 23.11 GFLOPS | Progress: (16/20) | 10.13 s
-[Task 2/25] Current/Best: 6.38/ 23.11 GFLOPS | Progress: (20/20) | 13.42 s Done.
+[Task 2/25] Current/Best: 5.70/ 14.21 GFLOPS | Progress: (4/20) | 4.10 s
+[Task 2/25] Current/Best: 6.25/ 16.86 GFLOPS | Progress: (8/20) | 5.74 s
+[Task 2/25] Current/Best: 6.55/ 16.86 GFLOPS | Progress: (12/20) | 7.57 s
+[Task 2/25] Current/Best: 8.14/ 16.86 GFLOPS | Progress: (16/20) | 9.51 s
+[Task 2/25] Current/Best: 21.40/ 21.40 GFLOPS | Progress: (20/20) | 11.51 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 14.53/ 14.53 GFLOPS | Progress: (4/20) | 4.09 s
-[Task 3/25] Current/Best: 19.15/ 19.91 GFLOPS | Progress: (8/20) | 6.43 s
-[Task 3/25] Current/Best: 5.42/ 19.91 GFLOPS | Progress: (12/20) | 10.57 s
-[Task 3/25] Current/Best: 17.95/ 19.91 GFLOPS | Progress: (16/20) | 13.52 s
-[Task 3/25] Current/Best: 8.57/ 19.91 GFLOPS | Progress: (20/20) | 16.12 s Done.
+[Task 3/25] Current/Best: 15.27/ 16.85 GFLOPS | Progress: (4/20) | 3.98 s
+[Task 3/25] Current/Best: 13.51/ 22.07 GFLOPS | Progress: (8/20) | 6.52 s
+[Task 3/25] Current/Best: 15.21/ 22.07 GFLOPS | Progress: (12/20) | 9.12 s
+[Task 3/25] Current/Best: 12.66/ 22.07 GFLOPS | Progress: (16/20) | 11.61 s
+[Task 3/25] Current/Best: 6.21/ 22.07 GFLOPS | Progress: (20/20) | 13.79 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 12.24/ 13.41 GFLOPS | Progress: (4/20) | 4.88 s
-[Task 4/25] Current/Best: 17.29/ 17.29 GFLOPS | Progress: (8/20) | 10.41 s
-[Task 4/25] Current/Best: 9.97/ 17.29 GFLOPS | Progress: (12/20) | 12.69 s
-[Task 4/25] Current/Best: 5.74/ 17.29 GFLOPS | Progress: (16/20) | 15.05 s
-[Task 4/25] Current/Best: 17.47/ 17.47 GFLOPS | Progress: (20/20) | 18.48 s Done.
+[Task 4/25] Current/Best: 10.97/ 15.40 GFLOPS | Progress: (4/20) | 7.82 s
+[Task 4/25] Current/Best: 8.13/ 19.55 GFLOPS | Progress: (8/20) | 10.65 s
+[Task 4/25] Current/Best: 10.03/ 19.55 GFLOPS | Progress: (12/20) | 15.74 s
+[Task 4/25] Current/Best: 9.75/ 19.55 GFLOPS | Progress: (16/20) | 18.45 s
+[Task 4/25] Current/Best: 17.34/ 19.55 GFLOPS | Progress: (20/20) | 20.57 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 11.11/ 11.15 GFLOPS | Progress: (4/20) | 4.26 s
-[Task 5/25] Current/Best: 7.73/ 22.19 GFLOPS | Progress: (8/20) | 5.90 s
-[Task 5/25] Current/Best: 4.58/ 22.19 GFLOPS | Progress: (12/20) | 8.72 s
-[Task 5/25] Current/Best: 14.28/ 22.19 GFLOPS | Progress: (16/20) | 11.13 s
-[Task 5/25] Current/Best: 17.82/ 22.19 GFLOPS | Progress: (20/20) | 12.85 s Done.
+[Task 5/25] Current/Best: 11.14/ 19.09 GFLOPS | Progress: (4/20) | 3.98 s
+[Task 5/25] Current/Best: 10.33/ 19.09 GFLOPS | Progress: (8/20) | 6.28 s
+[Task 5/25] Current/Best: 13.30/ 20.65 GFLOPS | Progress: (12/20) | 8.74 s
+[Task 5/25] Current/Best: 5.67/ 20.65 GFLOPS | Progress: (16/20) | 11.69 s
+[Task 5/25] Current/Best: 8.50/ 20.65 GFLOPS | Progress: (20/20) | 13.53 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.84/ 17.04 GFLOPS | Progress: (4/20) | 4.29 s
-[Task 6/25] Current/Best: 13.56/ 18.23 GFLOPS | Progress: (8/20) | 6.89 s
-[Task 6/25] Current/Best: 12.85/ 18.23 GFLOPS | Progress: (12/20) | 9.64 s
-[Task 6/25] Current/Best: 3.70/ 18.23 GFLOPS | Progress: (16/20) | 12.40 s
-[Task 6/25] Current/Best: 21.86/ 21.86 GFLOPS | Progress: (20/20) | 14.71 s Done.
+[Task 6/25] Current/Best: 16.67/ 16.67 GFLOPS | Progress: (4/20) | 7.06 s
+[Task 6/25] Current/Best: 21.94/ 21.94 GFLOPS | Progress: (8/20) | 9.41 s
+[Task 6/25] Current/Best: 17.94/ 21.94 GFLOPS | Progress: (12/20) | 11.87 s
+[Task 6/25] Current/Best: 15.14/ 21.94 GFLOPS | Progress: (16/20) | 14.80 s
+[Task 6/25] Current/Best: 5.57/ 21.94 GFLOPS | Progress: (20/20) | 18.71 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 15.80/ 15.90 GFLOPS | Progress: (4/20) | 5.62 s
-[Task 7/25] Current/Best: 22.90/ 22.90 GFLOPS | Progress: (8/20) | 7.58 s
-[Task 7/25] Current/Best: 14.96/ 22.90 GFLOPS | Progress: (12/20) | 9.96 s
-[Task 7/25] Current/Best: 8.71/ 22.90 GFLOPS | Progress: (16/20) | 14.23 s
-[Task 7/25] Current/Best: 6.22/ 22.90 GFLOPS | Progress: (20/20) | 16.87 s Done.
+[Task 7/25] Current/Best: 16.20/ 19.34 GFLOPS | Progress: (4/20) | 3.71 s
+[Task 7/25] Current/Best: 12.11/ 19.34 GFLOPS | Progress: (8/20) | 6.98 s
+[Task 7/25] Current/Best: 10.29/ 19.34 GFLOPS | Progress: (12/20) | 9.04 s
+[Task 7/25] Current/Best: 8.57/ 19.34 GFLOPS | Progress: (16/20) | 11.57 s
+[Task 7/25] Current/Best: 16.96/ 19.34 GFLOPS | Progress: (20/20) | 13.92 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 7.19/ 13.81 GFLOPS | Progress: (4/20) | 4.24 s
-[Task 8/25] Current/Best: 7.64/ 16.39 GFLOPS | Progress: (8/20) | 15.99 s
-[Task 8/25] Current/Best: 13.62/ 17.86 GFLOPS | Progress: (12/20) | 20.09 s
-[Task 8/25] Current/Best: 10.90/ 17.86 GFLOPS | Progress: (16/20) | 26.16 s
-[Task 8/25] Current/Best: 16.35/ 17.86 GFLOPS | Progress: (20/20) | 30.07 s
+[Task 8/25] Current/Best: 15.47/ 15.47 GFLOPS | Progress: (4/20) | 7.27 s
+[Task 8/25] Current/Best: 10.92/ 15.47 GFLOPS | Progress: (8/20) | 10.73 s
+[Task 8/25] Current/Best: 12.39/ 15.47 GFLOPS | Progress: (12/20) | 14.05 s
+[Task 8/25] Current/Best: 5.19/ 15.79 GFLOPS | Progress: (16/20) | 20.29 s
+[Task 8/25] Current/Best: 15.01/ 18.50 GFLOPS | Progress: (20/20) | 26.28 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 7.70/ 17.90 GFLOPS | Progress: (4/20) | 5.71 s
-[Task 9/25] Current/Best: 9.30/ 17.90 GFLOPS | Progress: (8/20) | 7.32 s
-[Task 9/25] Current/Best: 20.53/ 20.53 GFLOPS | Progress: (12/20) | 9.16 s
-[Task 9/25] Current/Best: 9.18/ 20.53 GFLOPS | Progress: (16/20) | 20.31 s
-[Task 9/25] Current/Best: 16.33/ 20.53 GFLOPS | Progress: (20/20) | 31.43 s
-[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 3.14/ 11.87 GFLOPS | Progress: (4/20) | 4.50 s Done.
- Done.
+[Task 9/25] Current/Best: 7.67/ 10.51 GFLOPS | Progress: (4/20) | 9.85 s
+[Task 9/25] Current/Best: 14.15/ 14.51 GFLOPS | Progress: (8/20) | 13.63 s
+[Task 9/25] Current/Best: 6.97/ 22.46 GFLOPS | Progress: (12/20) | 15.28 s
+[Task 9/25] Current/Best: 22.33/ 22.46 GFLOPS | Progress: (16/20) | 16.82 s
+[Task 9/25] Current/Best: 16.76/ 22.46 GFLOPS | Progress: (20/20) | 18.80 s Done.
-[Task 10/25] Current/Best: 8.04/ 15.44 GFLOPS | Progress: (8/20) | 6.27 s
-[Task 10/25] Current/Best: 7.88/ 18.49 GFLOPS | Progress: (12/20) | 10.09 s
-[Task 10/25] Current/Best: 18.93/ 18.93 GFLOPS | Progress: (16/20) | 11.96 s
-[Task 10/25] Current/Best: 11.22/ 18.93 GFLOPS | Progress: (20/20) | 13.97 s Done.
+[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 10/25] Current/Best: 2.98/ 17.65 GFLOPS | Progress: (4/20) | 4.28 s
+[Task 10/25] Current/Best: 8.36/ 17.65 GFLOPS | Progress: (8/20) | 6.22 s
+[Task 10/25] Current/Best: 14.58/ 17.65 GFLOPS | Progress: (12/20) | 8.61 s
+[Task 10/25] Current/Best: 3.28/ 17.65 GFLOPS | Progress: (16/20) | 10.56 s
+[Task 10/25] Current/Best: 10.28/ 17.65 GFLOPS | Progress: (20/20) | 12.43 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 23.73/ 23.73 GFLOPS | Progress: (4/20) | 4.40 s
-[Task 11/25] Current/Best: 15.72/ 23.73 GFLOPS | Progress: (8/20) | 6.90 s
-[Task 11/25] Current/Best: 21.51/ 23.73 GFLOPS | Progress: (12/20) | 9.43 s
-[Task 11/25] Current/Best: 17.40/ 23.73 GFLOPS | Progress: (16/20) | 11.38 s
-[Task 11/25] Current/Best: 23.19/ 23.73 GFLOPS | Progress: (20/20) | 13.37 s Done.
+[Task 11/25] Current/Best: 9.29/ 23.55 GFLOPS | Progress: (4/20) | 4.06 s
+[Task 11/25] Current/Best: 15.86/ 23.55 GFLOPS | Progress: (8/20) | 6.33 s
+[Task 11/25] Current/Best: 1.57/ 23.55 GFLOPS | Progress: (12/20) | 9.85 s
+[Task 11/25] Current/Best: 12.33/ 23.55 GFLOPS | Progress: (16/20) | 12.27 s
+[Task 11/25] Current/Best: 22.32/ 23.55 GFLOPS | Progress: (20/20) | 14.37 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 10.07/ 19.30 GFLOPS | Progress: (4/20) | 4.51 s
-[Task 12/25] Current/Best: 15.84/ 19.30 GFLOPS | Progress: (8/20) | 8.14 s
-[Task 12/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (12/20) | 11.87 s
-[Task 12/25] Current/Best: 5.11/ 20.66 GFLOPS | Progress: (16/20) | 14.20 s
-[Task 12/25] Current/Best: 15.43/ 20.66 GFLOPS | Progress: (20/20) | 21.44 s Done.
+[Task 12/25] Current/Best: 4.39/ 20.86 GFLOPS | Progress: (4/20) | 4.17 s
+[Task 12/25] Current/Best: 14.61/ 20.86 GFLOPS | Progress: (8/20) | 6.42 s
+[Task 12/25] Current/Best: 10.34/ 20.86 GFLOPS | Progress: (12/20) | 9.82 s
+[Task 12/25] Current/Best: 13.98/ 20.86 GFLOPS | Progress: (16/20) | 12.15 s
+[Task 12/25] Current/Best: 10.42/ 20.86 GFLOPS | Progress: (20/20) | 14.48 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 7.37/ 17.24 GFLOPS | Progress: (4/20) | 5.10 s
-[Task 13/25] Current/Best: 17.48/ 17.48 GFLOPS | Progress: (8/20) | 8.70 s
-[Task 13/25] Current/Best: 3.10/ 20.62 GFLOPS | Progress: (12/20) | 12.38 s
-[Task 13/25] Current/Best: 3.09/ 20.62 GFLOPS | Progress: (16/20) | 15.49 s
-[Task 13/25] Current/Best: 8.74/ 20.62 GFLOPS | Progress: (20/20) | 19.27 s Done.
+[Task 13/25] Current/Best: 9.31/ 10.23 GFLOPS | Progress: (4/20) | 5.39 s
+[Task 13/25] Current/Best: 6.91/ 18.36 GFLOPS | Progress: (8/20) | 8.53 s
+[Task 13/25] Current/Best: 7.46/ 18.36 GFLOPS | Progress: (12/20) | 11.32 s
+[Task 13/25] Current/Best: 6.12/ 19.30 GFLOPS | Progress: (16/20) | 13.98 s
+[Task 13/25] Current/Best: 16.69/ 19.30 GFLOPS | Progress: (20/20) | 16.76 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 11.40/ 12.53 GFLOPS | Progress: (4/20) | 4.38 s
-[Task 14/25] Current/Best: 15.51/ 18.28 GFLOPS | Progress: (8/20) | 10.40 s
-[Task 14/25] Current/Best: 14.74/ 18.28 GFLOPS | Progress: (12/20) | 13.82 s
-[Task 14/25] Current/Best: 11.09/ 18.28 GFLOPS | Progress: (16/20) | 16.77 s
-[Task 14/25] Current/Best: 4.88/ 18.28 GFLOPS | Progress: (20/20) | 20.61 s
+[Task 14/25] Current/Best: 11.56/ 16.72 GFLOPS | Progress: (4/20) | 5.46 s
+[Task 14/25] Current/Best: 9.70/ 16.72 GFLOPS | Progress: (8/20) | 8.13 s
+[Task 14/25] Current/Best: 11.16/ 21.93 GFLOPS | Progress: (12/20) | 10.04 s
+[Task 14/25] Current/Best: 3.15/ 21.93 GFLOPS | Progress: (16/20) | 12.88 s
+[Task 14/25] Current/Best: 10.68/ 21.93 GFLOPS | Progress: (20/20) | 15.69 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 20.14/ 20.14 GFLOPS | Progress: (4/20) | 5.16 s
-[Task 15/25] Current/Best: 21.21/ 21.21 GFLOPS | Progress: (8/20) | 7.39 s
-[Task 15/25] Current/Best: 5.71/ 21.21 GFLOPS | Progress: (12/20) | 14.86 s
-[Task 15/25] Current/Best: 16.92/ 21.21 GFLOPS | Progress: (16/20) | 16.63 s
-[Task 15/25] Current/Best: 12.51/ 21.21 GFLOPS | Progress: (20/20) | 18.24 s
-[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 15.81/ 15.81 GFLOPS | Progress: (4/20) | 4.47 s
-[Task 16/25] Current/Best: 13.17/ 21.12 GFLOPS | Progress: (8/20) | 6.80 s Done.
- Done.
+[Task 15/25] Current/Best: 13.30/ 15.41 GFLOPS | Progress: (4/20) | 3.90 s
+[Task 15/25] Current/Best: 11.19/ 15.41 GFLOPS | Progress: (8/20) | 6.90 s
+[Task 15/25] Current/Best: 14.53/ 15.41 GFLOPS | Progress: (12/20) | 10.03 s
+[Task 15/25] Current/Best: 19.65/ 19.65 GFLOPS | Progress: (16/20) | 13.38 s
+[Task 15/25] Current/Best: 10.28/ 19.65 GFLOPS | Progress: (20/20) | 17.27 s Done.
-[Task 16/25] Current/Best: 10.57/ 21.12 GFLOPS | Progress: (12/20) | 9.65 s
-[Task 16/25] Current/Best: 16.73/ 21.12 GFLOPS | Progress: (16/20) | 13.67 s
-[Task 16/25] Current/Best: 10.24/ 21.12 GFLOPS | Progress: (20/20) | 15.59 s Done.
+[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 16/25] Current/Best: 10.24/ 18.11 GFLOPS | Progress: (4/20) | 5.76 s
+[Task 16/25] Current/Best: 13.82/ 20.57 GFLOPS | Progress: (8/20) | 7.36 s
+[Task 16/25] Current/Best: 6.58/ 20.57 GFLOPS | Progress: (12/20) | 9.36 s
+[Task 16/25] Current/Best: 7.90/ 20.57 GFLOPS | Progress: (16/20) | 13.86 s
+[Task 16/25] Current/Best: 14.50/ 20.57 GFLOPS | Progress: (20/20) | 17.05 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 20.14/ 21.92 GFLOPS | Progress: (4/20) | 4.33 s
-[Task 17/25] Current/Best: 17.78/ 21.92 GFLOPS | Progress: (8/20) | 6.66 s
-[Task 17/25] Current/Best: 17.84/ 21.92 GFLOPS | Progress: (12/20) | 9.39 s
-[Task 17/25] Current/Best: 8.77/ 21.92 GFLOPS | Progress: (16/20) | 11.91 s
-[Task 17/25] Current/Best: 9.90/ 21.92 GFLOPS | Progress: (20/20) | 15.36 s Done.
+[Task 17/25] Current/Best: 7.63/ 12.68 GFLOPS | Progress: (4/20) | 4.83 s
+[Task 17/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (8/20) | 8.06 s
+[Task 17/25] Current/Best: 20.92/ 20.92 GFLOPS | Progress: (12/20) | 12.25 s
+[Task 17/25] Current/Best: 12.30/ 20.92 GFLOPS | Progress: (16/20) | 14.64 s
+[Task 17/25] Current/Best: 16.26/ 20.92 GFLOPS | Progress: (20/20) | 17.20 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 15.86/ 15.86 GFLOPS | Progress: (4/20) | 8.41 s
-[Task 18/25] Current/Best: 17.87/ 17.95 GFLOPS | Progress: (8/20) | 10.41 s
-[Task 18/25] Current/Best: 11.67/ 18.76 GFLOPS | Progress: (12/20) | 13.04 s
-[Task 18/25] Current/Best: 13.48/ 18.76 GFLOPS | Progress: (16/20) | 15.76 s
-[Task 18/25] Current/Best: 19.88/ 20.35 GFLOPS | Progress: (20/20) | 18.15 s Done.
+[Task 18/25] Current/Best: 13.11/ 20.08 GFLOPS | Progress: (4/20) | 3.78 s
+[Task 18/25] Current/Best: 18.25/ 20.35 GFLOPS | Progress: (8/20) | 5.58 s
+[Task 18/25] Current/Best: 17.47/ 20.35 GFLOPS | Progress: (12/20) | 7.34 s
+[Task 18/25] Current/Best: 12.91/ 20.35 GFLOPS | Progress: (16/20) | 9.52 s
+[Task 18/25] Current/Best: 9.62/ 20.35 GFLOPS | Progress: (20/20) | 12.94 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 17.61/ 18.46 GFLOPS | Progress: (4/20) | 6.23 s
-[Task 19/25] Current/Best: 10.93/ 18.46 GFLOPS | Progress: (8/20) | 10.23 s
-[Task 19/25] Current/Best: 12.40/ 21.03 GFLOPS | Progress: (12/20) | 12.97 s
-[Task 19/25] Current/Best: 21.53/ 21.53 GFLOPS | Progress: (16/20) | 15.46 s
-[Task 19/25] Current/Best: 18.53/ 21.53 GFLOPS | Progress: (20/20) | 18.18 s Done.
+[Task 19/25] Current/Best: 2.68/ 18.61 GFLOPS | Progress: (4/20) | 5.57 s
+[Task 19/25] Current/Best: 17.89/ 18.61 GFLOPS | Progress: (8/20) | 9.49 s
+[Task 19/25] Current/Best: 9.19/ 18.61 GFLOPS | Progress: (12/20) | 12.01 s
+[Task 19/25] Current/Best: 1.55/ 18.61 GFLOPS | Progress: (16/20) | 16.91 s
+[Task 19/25] Current/Best: 19.10/ 19.10 GFLOPS | Progress: (20/20) | 19.50 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 10.00/ 12.20 GFLOPS | Progress: (4/20) | 5.63 s
-[Task 20/25] Current/Best: 5.33/ 12.53 GFLOPS | Progress: (8/20) | 8.23 s
-[Task 20/25] Current/Best: 15.05/ 15.05 GFLOPS | Progress: (12/20) | 11.47 s
-[Task 20/25] Current/Best: 15.41/ 15.90 GFLOPS | Progress: (16/20) | 13.95 s
-[Task 20/25] Current/Best: 9.58/ 16.13 GFLOPS | Progress: (20/20) | 16.76 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 17.79/ 17.79 GFLOPS | Progress: (4/20) | 7.40 s
-[Task 21/25] Current/Best: 12.38/ 19.19 GFLOPS | Progress: (8/20) | 9.33 s
-[Task 21/25] Current/Best: 16.61/ 19.19 GFLOPS | Progress: (12/20) | 11.92 s
-[Task 21/25] Current/Best: 14.35/ 19.19 GFLOPS | Progress: (16/20) | 14.19 s Done.
-
-[Task 21/25] Current/Best: 5.35/ 19.19 GFLOPS | Progress: (20/20) | 15.64 s
+[Task 20/25] Current/Best: 11.28/ 11.55 GFLOPS | Progress: (4/20) | 5.83 s
+[Task 20/25] Current/Best: 13.86/ 14.85 GFLOPS | Progress: (8/20) | 8.22 s
+[Task 20/25] Current/Best: 6.48/ 14.85 GFLOPS | Progress: (12/20) | 10.55 s
+[Task 20/25] Current/Best: 13.68/ 17.78 GFLOPS | Progress: (16/20) | 14.01 s
+[Task 20/25] Current/Best: 16.73/ 17.78 GFLOPS | Progress: (20/20) | 16.44 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 21/25] Current/Best: 16.95/ 16.95 GFLOPS | Progress: (4/20) | 4.15 s
+[Task 21/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (8/20) | 7.14 s
+[Task 21/25] Current/Best: 8.88/ 18.79 GFLOPS | Progress: (12/20) | 8.74 s
+[Task 21/25] Current/Best: 2.70/ 18.79 GFLOPS | Progress: (16/20) | 11.14 s
+[Task 21/25] Current/Best: 13.40/ 18.79 GFLOPS | Progress: (20/20) | 13.60 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 18.13/ 18.13 GFLOPS | Progress: (4/20) | 4.73 s
-[Task 22/25] Current/Best: 10.14/ 19.01 GFLOPS | Progress: (8/20) | 7.51 s
-[Task 22/25] Current/Best: 6.67/ 20.06 GFLOPS | Progress: (12/20) | 9.97 s
-[Task 22/25] Current/Best: 14.75/ 20.55 GFLOPS | Progress: (16/20) | 11.59 s
-[Task 22/25] Current/Best: 15.34/ 20.55 GFLOPS | Progress: (20/20) | 15.82 s Done.
+[Task 22/25] Current/Best: 6.34/ 11.62 GFLOPS | Progress: (4/20) | 4.80 s
+[Task 22/25] Current/Best: 8.00/ 16.25 GFLOPS | Progress: (8/20) | 7.47 s
+[Task 22/25] Current/Best: 7.97/ 17.98 GFLOPS | Progress: (12/20) | 10.11 s
+[Task 22/25] Current/Best: 7.94/ 17.98 GFLOPS | Progress: (16/20) | 12.27 s
+[Task 22/25] Current/Best: 4.54/ 20.67 GFLOPS | Progress: (20/20) | 17.21 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 1.55/ 23.38 GFLOPS | Progress: (4/20) | 5.84 s
-[Task 23/25] Current/Best: 10.66/ 23.38 GFLOPS | Progress: (8/20) | 8.51 s
-[Task 23/25] Current/Best: 1.55/ 23.38 GFLOPS | Progress: (12/20) | 12.80 s
-[Task 23/25] Current/Best: 19.41/ 23.38 GFLOPS | Progress: (16/20) | 20.74 s
-[Task 23/25] Current/Best: 17.82/ 23.38 GFLOPS | Progress: (20/20) | 23.33 s Done.
+[Task 23/25] Current/Best: 19.90/ 19.91 GFLOPS | Progress: (4/20) | 4.25 s
+[Task 23/25] Current/Best: 5.34/ 19.91 GFLOPS | Progress: (8/20) | 6.80 s
+[Task 23/25] Current/Best: 6.11/ 19.91 GFLOPS | Progress: (12/20) | 9.65 s
+[Task 23/25] Current/Best: 13.13/ 22.90 GFLOPS | Progress: (16/20) | 13.23 s
+[Task 23/25] Current/Best: 19.34/ 22.90 GFLOPS | Progress: (20/20) | 16.45 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 5.65/ 5.77 GFLOPS | Progress: (4/20) | 12.52 s
-[Task 24/25] Current/Best: 2.93/ 8.73 GFLOPS | Progress: (8/20) | 19.77 s
-[Task 24/25] Current/Best: 6.78/ 8.73 GFLOPS | Progress: (12/20) | 30.75 s
-[Task 24/25] Current/Best: 3.09/ 8.77 GFLOPS | Progress: (16/20) | 41.41 s
-[Task 24/25] Current/Best: 1.70/ 8.77 GFLOPS | Progress: (20/20) | 53.61 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
-[Task 25/25] Current/Best: 2.99/ 8.53 GFLOPS | Progress: (4/20) | 12.82 s
-[Task 25/25] Current/Best: 7.88/ 8.53 GFLOPS | Progress: (8/20) | 23.79 s
-[Task 25/25] Current/Best: 1.55/ 8.63 GFLOPS | Progress: (12/20) | 34.76 s
-[Task 25/25] Current/Best: 8.72/ 8.72 GFLOPS | Progress: (16/20) | 38.97 s
-[Task 25/25] Current/Best: 5.62/ 9.21 GFLOPS | Progress: (20/20) | 40.35 s
+[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (4/20) | 11.85 s
+[Task 24/25] Current/Best: 3.57/ 7.40 GFLOPS | Progress: (8/20) | 23.99 s
+[Task 24/25] Current/Best: 9.64/ 9.64 GFLOPS | Progress: (12/20) | 34.93 s Done.
+
+[Task 24/25] Current/Best: 2.29/ 10.71 GFLOPS | Progress: (16/20) | 45.88 s
+[Task 24/25] Current/Best: 6.94/ 10.71 GFLOPS | Progress: (20/20) | 56.83 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 8.94/ 9.24 GFLOPS | Progress: (4/20) | 13.85 s
+[Task 25/25] Current/Best: 5.93/ 9.24 GFLOPS | Progress: (8/20) | 24.78 s
+[Task 25/25] Current/Best: 6.26/ 9.24 GFLOPS | Progress: (12/20) | 29.32 s
+[Task 25/25] Current/Best: 7.94/ 9.24 GFLOPS | Progress: (16/20) | 40.25 s
+[Task 25/25] Current/Best: 5.92/ 9.24 GFLOPS | Progress: (20/20) | 51.19 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -982,8 +982,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 423.5480854100001, 'median': 423.5180550500104, 'std': 3.025069320486451}
-unoptimized: {'mean': 515.7709692800006, 'median': 515.0009511999997, 'std': 2.2209522109315}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 412.4336003600001, 'median': 412.09299079999937, 'std': 1.9291336960928867}
+unoptimized: {'mean': 512.1992977499997, 'median': 511.0846481500005, 'std': 2.718325039446462}
</pre></div>
</div>
</div>
@@ -997,7 +997,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 6.435 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 33.016 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 7038d97ad7..3d78cbb69b 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -537,7 +537,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.242e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.287e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 96979b801f..87020085e7 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -494,7 +494,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x2375ffe0)), stage(b, placeholder(b, 0x20d0b990)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x2187dbd0)), stage(b, placeholder(b, 0x4b5c8e0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 8a5f21112f..9513184ba3 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:31.930</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>14:49.341</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,43 +349,43 @@
</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>12:06.435</p></td>
+<td><p>11:33.016</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>01:29.595</p></td>
+<td><p>01:16.697</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.401</p></td>
+<td><p>00:58.150</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>00:34.379</p></td>
+<td><p>00:33.483</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>00:18.618</p></td>
+<td><p>00:23.711</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>00:01.464</p></td>
+<td><p>00:03.295</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>00:00.845</p></td>
+<td><p>00:00.818</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>00:00.180</p></td>
+<td><p>00:00.162</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
-<td><p>00:00.008</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
-<td><p>00:00.001</p></td>
+<td><p>00:00.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index dc631eb126..1287c2fa4a 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -551,7 +551,7 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
naive: 0.000007
</pre></div>
</div>
@@ -600,7 +600,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000008
</pre></div>
</div>
</div>
@@ -671,10 +671,10 @@ factor to be the number of threads on your CPU.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.922929999040207e-06 1.0
- naive 6.755800000000001e-06 0.8526895985220627
-parallel 6.9898e-06 0.8822241267872811
- vector 2.45943e-05 3.104192515013938
+ numpy 6.807869999647664e-06 1.0
+ naive 6.9094e-06 1.0149136220811488
+parallel 8.2734e-06 1.2152699743720403
+ vector 2.46488e-05 3.6206331791405653
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -990,7 +990,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018479
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018272
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1031,7 +1031,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.342083
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.205106
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1095,7 +1095,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.312642
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.296652
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1153,7 +1153,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.348580
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.332271
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1207,7 +1207,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116981
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.115928
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1282,7 +1282,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108607
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108467
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1355,7 +1355,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111039
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110566
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146690
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145482
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1024, 1024], []),
@@ -1482,13 +1482,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.3420834258 1.0
- blocking 0.3126420623 0.09354705507543169
- vectorization 0.3485796604 0.10430010744467276
-loop permutation 0.11698097410000001 0.03500240993295914
- array packing 0.1086071926 0.03249685264035637
- block caching 0.11103898990000001 0.033224481783670747
- parallelization 0.1466900011 0.04389178318159026
+ none 3.20510635 1.0
+ blocking 0.2966517709 0.09255598364154126
+ vectorization 0.3322708254 0.10366920442437114
+loop permutation 0.11592775500000001 0.0361697061939926
+ array packing 0.10846665370000001 0.03384182671504801
+ block caching 0.1105661145 0.034496862951209094
+ parallelization 0.1454820974 0.045390723899068126
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1520,7 +1520,6 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.401 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>