You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/04/11 09:58:23 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@f79e4ebf30ebaac2fc61f690629efff6b7f8a890)
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 cb32f50053 deploying docs (apache/tvm@f79e4ebf30ebaac2fc61f690629efff6b7f8a890)
cb32f50053 is described below
commit cb32f50053137bd53dc007e4e191ae2aea058f94
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Apr 11 09:58:13 2023 +0000
deploying docs (apache/tvm@f79e4ebf30ebaac2fc61f690629efff6b7f8a890)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 333957 -> 348666 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23827 -> 24386 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_model_on_adreno_tvmc.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 22 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 894 ++++++++++++++++++---
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 48 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 550 ++++++++++++-
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 14 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 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 | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 16 +-
docs/how_to/compile_models/from_pytorch.html | 12 +-
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_adreno_tvmc.html | 35 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 59 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 894 ++++++++++++++++++---
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 48 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 550 ++++++++++++-
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
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 | 14 +-
.../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/install/nnpack.html | 12 +-
.../api/doxygen/detail_2extern_8h_source.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
docs/reference/api/typedoc/classes/instance.html | 58 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
.../api/typedoc/classes/runtimecontext.html | 22 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
docs/reference/api/typedoc/classes/tvmarray.html | 16 +-
docs/reference/api/typedoc/classes/tvmobject.html | 12 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 124 +--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 10 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 270 +++----
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 | 44 +-
131 files changed, 3541 insertions(+), 1192 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index b0c19c3436..b353dd858a 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 475ea5ff8a..280b5c012d 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 045ebb92d9..32f09e650d 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.885 seconds)
+ **Total running time of the script:** ( 1 minutes 21.215 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index bf36e9024a..006d6224a3 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -116,7 +116,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1f3ea56b-9275-4776-8673-d5915cd2a69d from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip606b9c7c-de5f-48a2-900e-35609aefaa43 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 5fb230eb5b..be444918f9 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 59.3MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 41.5MB/s]
45%|####4 | 18.5M/41.5M [00:00<00:00, 41.9MB/s]
55%|#####4 | 22.6M/41.5M [00:00<00:00, 32.6MB/s]
63%|######2 | 26.0M/41.5M [00:00<00:00, 24.5MB/s]
77%|#######7 | 32.0M/41.5M [00:01<00:00, 27.0MB/s]
96%|#########6| 40.0M/41.5M [00:01<00:00, 37.6MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 36.3MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 41.6MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 37.3MB/s]
43%|####3 | 17.9M/41.5M [00:00<00:00, 34.8MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 35.4MB/s]
62%|######1 | 25.7M/41.5M [00:00<00:00, 32.5MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.3MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 45.5MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 39.6MB/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 b1ae357493..97bbaa32fc 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 55.7MB/s]
30%|##9 | 13.3M/44.7M [00:00<00:00, 45.8MB/s]
40%|###9 | 17.7M/44.7M [00:00<00:00, 37.3MB/s]
54%|#####3 | 24.1M/44.7M [00:00<00:00, 46.3MB/s]
78%|#######8 | 34.9M/44.7M [00:00<00:00, 66.1MB/s]
94%|#########3| 41.8M/44.7M [00:00<00:00, 67.9MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 54.5MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 59.6MB/s]
40%|#### | 18.1M/44.7M [00:00<00:00, 80.4MB/s]
61%|######1 | 27.5M/44.7M [00:00<00:00, 87.9MB/s]
90%|########9 | 40.0M/44.7M [00:00<00:00, 93.2MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 88.8MB/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 b851f464f9..9e60df34a9 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -430,7 +430,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 32.798 seconds)
+ **Total running time of the script:** ( 1 minutes 30.065 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 e4ef77d25c..8ba02eeb9b 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**06:53.125** total execution time for **how_to_compile_models** files:
+**06:48.847** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:32.798 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:30.065 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:22.885 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:21.215 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:55.295 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:56.595 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:37.852 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.016 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.663 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:31.665 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.788 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.242 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:28.828 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:28.087 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.366 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:25.858 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:22.884 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:24.366 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.767 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.739 | 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 33656693a8..d2b08b3c48 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -637,7 +637,7 @@ 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)
- 2636.3413 2635.8546 2640.6695 2634.9949 1.5893
+ 2679.8810 2679.4614 2683.8909 2678.6685 1.4501
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
index b11fe6ed87..b1e2c5fc6d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
@@ -127,7 +127,7 @@ Make a Keras Resnet50 Model
.. code-block:: none
Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
-
8192/102967424 [..............................] - ETA: 0s
9666560/102967424 [=>............................] - ETA: 0s
16769024/102967424 [===>..........................] - ETA: 0s
25157632/102967424 [======>.......................] - ETA: 0s
33546240/102967424 [========>.....................] - ETA: 0s
39223296/102967424 [==========>...................] - ETA: 0s
41934848/102967424 [===========>..................] - ETA: 0s
48578560/102967424 [=============>................] - ETA: 0s
52518912/102967424 [==============>...............] - ETA: 0s
63627264/102967424 [=================>............] - ETA: 0s
68599808/102967424 [==================>...........] - ETA: 0s
73605120/102967424 [====================>.........] - ETA: 0s
77971456/102967424 [=====================>........] - ETA: 0s
83623936/102967424 [=======================>......] - ETA: 0s
88645632/102967424 [========================>.....] - ETA: 0s
93618176/102967424 [==========================>...] -
ETA: 0s
94461952/102967424 [==========================>...] - ETA: 0s
100646912/102967424 [============================>.] - ETA: 0s
102850560/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
+
8192/102967424 [..............................] - ETA: 0s
8380416/102967424 [=>............................] - ETA: 1s
16769024/102967424 [===>..........................] - ETA: 1s
23412736/102967424 [=====>........................] - ETA: 0s
25157632/102967424 [======>.......................] - ETA: 1s
33546240/102967424 [========>.....................] - ETA: 1s
40189952/102967424 [==========>...................] - ETA: 0s
41934848/102967424 [===========>..................] - ETA: 0s
48578560/102967424 [=============>................] - ETA: 0s
50323456/102967424 [=============>................] - ETA: 0s
58712064/102967424 [================>.............] - ETA: 0s
65355776/102967424 [==================>...........] - ETA: 0s
67100672/102967424 [==================>...........] - ETA: 0s
69296128/102967424 [===================>..........] - ETA: 0s
71540736/102967424 [===================>..........] - ETA: 0s
75489280/102967424 [====================>.........] -
ETA: 0s
82124800/102967424 [======================>.......] - ETA: 0s
83877888/102967424 [=======================>......] - ETA: 0s
90521600/102967424 [=========================>....] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
98910208/102967424 [===========================>..] - ETA: 0s
100646912/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 2s 0us/step
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 5137001243..8654c1ce3f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 14.7598 14.6373 15.7451 14.4975 0.3477
+ 15.6998 15.6305 16.1354 15.5438 0.1791
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 8adc13e637..13e53662c6 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:02, 60.0MB/s]
7%|7 | 12.0M/170M [00:00<00:03, 54.0MB/s]
10%|# | 17.2M/170M [00:00<00:05, 27.6MB/s]
13%|#3 | 22.3M/170M [00:00<00:05, 25.8MB/s]
15%|#4 | 25.3M/170M [00:00<00:06, 24.1MB/s]
19%|#8 | 32.0M/170M [00:01<00:05, 25.5MB/s]
24%|##3 | 40.0M/170M [00:01<00:03, 34.1MB/s]
28%|##8 | 48.0M/170M [00:01<00:03, 39.3MB/s]
33%|###3 | 56.5M/170M [00:01<00:02, 49.3MB/s]
37%|###6 | 62.3M/170M [00:01<00:02, 47.0MB/s]
40%|###9 | 67.3M/170M [00:01<00:02, 47.9MB/s]
43%|####2 | 72.3M/170M [00:01<00:02, 46.9MB/s]
47%|####7 | 80.0M/170M [00:02<00:02, 44.0MB/s]
51%|##### | 86.3M/170M [00:02<00:01, 48.5MB/s]
54%|#####3 | 91.3M/170M [00:02<00:01, 44.8MB/s]
57%|#####6 | 96.0M/170M [00:02<00:01, 41.3MB/s]
59%|#####8 | 100M/170M [00:02<00:01, 40.6MB/s
]
61%|######1 | 104M/170M [00:02<00:02, 29.0MB/s]
66%|######5 | 112M/170M [00:03<00:01, 35.2MB/s]
71%|####### | 120M/170M [00:03<00:01, 39.0MB/s]
74%|#######4 | 126M/170M [00:03<00:01, 41.1MB/s]
77%|#######6 | 130M/170M [00:03<00:01, 37.0MB/s]
79%|#######9 | 134M/170M [00:03<00:01, 36.3MB/s]
81%|########1 | 138M/170M [00:03<00:00, 33.7MB/s]
85%|########4 | 144M/170M [00:03<00:00, 39.6MB/s]
89%|########9 | 152M/170M [00:04<00:00, 40.4MB/s]
93%|#########3| 158M/170M [00:04<00:00, 41.1MB/s]
96%|#########5| 162M/170M [00:04<00:00, 34.5MB/s]
99%|#########8| 168M/170M [00:04<00:00, 38.6MB/s]
100%|##########| 170M/170M [00:04<00:00, 38.6MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
3%|3 | 5.18M/170M [00:00<00:03, 51.3MB/s]
6%|5 | 10.1M/170M [00:00<00:04, 39.4MB/s]
9%|9 | 16.0M/170M [00:00<00:03, 44.0MB/s]
13%|#3 | 22.3M/170M [00:00<00:03, 44.7MB/s]
16%|#5 | 26.6M/170M [00:00<00:03, 44.6MB/s]
19%|#8 | 32.0M/170M [00:00<00:03, 39.1MB/s]
24%|##3 | 40.0M/170M [00:00<00:03, 45.0MB/s]
28%|##8 | 48.0M/170M [00:01<00:02, 49.1MB/s]
34%|###4 | 58.3M/170M [00:01<00:01, 63.2MB/s]
38%|###8 | 64.8M/170M [00:01<00:01, 60.2MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 63.0MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 57.7MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 53.7MB/s]
56%|#####5 | 94.3M/170M [00:01<00:01, 53.1MB/s]
59%|#####8 | 99.5M/170M [00:02<00:01, 51.3MB/s]
62%|######1 | 105M/170M [00:02<00:01, 39.6MB/s]
66%|######5 | 112M/170M [00:02<00:01, 45.9MB/s
]
71%|####### | 120M/170M [00:02<00:01, 49.2MB/s]
74%|#######4 | 126M/170M [00:02<00:00, 51.9MB/s]
77%|#######7 | 132M/170M [00:02<00:00, 52.1MB/s]
80%|######## | 137M/170M [00:02<00:00, 38.5MB/s]
85%|########4 | 144M/170M [00:03<00:00, 45.5MB/s]
89%|########9 | 152M/170M [00:03<00:00, 51.3MB/s]
93%|#########2| 157M/170M [00:03<00:00, 45.7MB/s]
95%|#########5| 162M/170M [00:03<00:00, 46.1MB/s]
99%|#########8| 168M/170M [00:03<00:00, 44.8MB/s]
100%|##########| 170M/170M [00:03<00:00, 48.7MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 30.808 seconds)
+ **Total running time of the script:** ( 3 minutes 33.022 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 c93c66bacf..c3be583b1b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
66%|######5 | 8.90M/13.6M [00:00<00:00, 93.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 62.3MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 62.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 58.6MB/s]
@@ -409,7 +409,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 88.0155 87.9377 92.8729 87.7785 0.5127
+ 90.3143 90.1681 98.6706 89.8865 0.8972
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 15.709 seconds)
+ **Total running time of the script:** ( 1 minutes 16.277 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 92e0c8787a..2545432a07 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -423,7 +423,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 117.1700 117.1899 118.1862 116.4393 0.2836
+ 118.4165 118.3799 123.2114 116.1521 1.0844
@@ -460,7 +460,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 27.391 seconds)
+ **Total running time of the script:** ( 2 minutes 28.227 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 dcf78e4a0b..bcdc385c71 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 43.421 seconds)
+ **Total running time of the script:** ( 1 minutes 48.070 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 c78f46165d..b3fddf82e0 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
1%|1 | 1364/132723 [00:00<00:09, 13620.56KB/s]
3%|3 | 4293/132723 [00:00<00:05, 22830.21KB/s]
7%|7 | 9328/132723 [00:00<00:03, 35128.75KB/s]
12%|#1 | 15863/132723 [00:00<00:02, 47001.88KB/s]
18%|#8 | 24515/132723 [00:00<00:01, 61207.79KB/s]
25%|##5 | 33200/132723 [00:00<00:01, 69899.40KB/s]
32%|###1 | 41904/132723 [00:00<00:01, 75493.12KB/s]
38%|###8 | 50569/132723 [00:00<00:01, 79040.31KB/s]
45%|####4 | 59306/132723 [00:00<00:00, 81641.28KB/s]
51%|#####1 | 68064/132723 [00:01<00:00, 83472.08KB/s]
58%|#####7 | 76830/132723 [00:01<00:00, 84749.90KB/s]
64%|######4 | 85307/132723 [00:01<00:00, 76070.74KB/s]
71%|####### | 94037/132723 [00:01<00:00, 79217.33KB/s]
77%|#######7 | 102800/132723 [00:01<00:00, 81622.85KB/s]
84%|########4 | 111559/132723 [00:01<00:00, 83352.52KB/s]
90%|######### |
119979/132723 [00:01<00:00, 78052.80KB/s]
97%|#########7| 128760/132723 [00:01<00:00, 80792.80KB/s]
100%|##########| 132723/132723 [00:01<00:00, 68842.75KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
1%| | 1304/132723 [00:00<00:10, 13006.34KB/s]
3%|3 | 4088/132723 [00:00<00:05, 21657.15KB/s]
7%|7 | 9793/132723 [00:00<00:03, 37780.29KB/s]
14%|#3 | 18341/132723 [00:00<00:02, 56583.47KB/s]
20%|## | 26924/132723 [00:00<00:01, 67117.91KB/s]
27%|##6 | 35418/132723 [00:00<00:01, 73170.84KB/s]
33%|###3 | 44025/132723 [00:00<00:01, 77377.58KB/s]
40%|###9 | 52634/132723 [00:00<00:00, 80148.72KB/s]
46%|####6 | 61265/132723 [00:00<00:00, 82070.78KB/s]
53%|#####2 | 69897/132723 [00:01<00:00, 83379.03KB/s]
59%|#####9 | 78466/132723 [00:01<00:00, 84084.85KB/s]
66%|######5 | 87065/132723 [00:01<00:00, 84662.28KB/s]
72%|#######2 | 95723/132723 [00:01<00:00, 85238.81KB/s]
79%|#######8 | 104248/132723 [00:01<00:00, 70780.99KB/s]
85%|########4 | 112197/132723 [00:01<00:00, 73075.63KB/s]
90%|######### |
119822/132723 [00:01<00:00, 52353.27KB/s]
97%|#########6| 128449/132723 [00:01<00:00, 59703.95KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67378.08KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 59.187 seconds)
+ **Total running time of the script:** ( 3 minutes 55.455 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 ac996a4417..fb509b4cf1 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
Computation times
=================
-**16:20.756** total execution time for **how_to_deploy_models** files:
+**16:27.773** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:59.187 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:55.455 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:30.808 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:33.022 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:27.391 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.227 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:43.421 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:48.070 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:15.709 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:16.277 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.776 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:56.392 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:50.440 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:51.909 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:42.477 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:42.620 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.095 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.102 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.447 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.692 | 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 f95f2330e4..a2f3806a8e 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -463,7 +463,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipaf5dd4c9-a675-4fbc-9418-72a52f0eea71 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipc93d54ad-2f79-452a-85a7-10ed78b12878 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 2405dbf647..7edb7632f9 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:55.415** total execution time for **how_to_extend_tvm** files:
+**00:53.883** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:51.557 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:50.143 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.768 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.684 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.083 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.049 | 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 d5ea54ada5..05f316bfa2 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -220,10 +220,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 22201us [22201us] (48.61%; 48.61%)
- FoldScaleAxis: 23474us [7us] (51.39%; 51.39%)
- FoldConstant: 23467us [1736us] (51.38%; 99.97%)
- InferType: 21731us [21731us] (47.58%; 92.60%)
+ InferType: 22194us [22194us] (48.80%; 48.80%)
+ FoldScaleAxis: 23286us [7us] (51.20%; 51.20%)
+ FoldConstant: 23279us [1675us] (51.18%; 99.97%)
+ InferType: 21604us [21604us] (47.50%; 92.80%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 21828us [21828us] (48.21%; 48.21%)
- FoldScaleAxis: 23451us [5us] (51.79%; 51.79%)
- FoldConstant: 23446us [1693us] (51.78%; 99.98%)
- InferType: 21753us [21753us] (48.04%; 92.78%)
+ InferType: 21621us [21621us] (48.34%; 48.34%)
+ FoldScaleAxis: 23102us [5us] (51.66%; 51.66%)
+ FoldConstant: 23097us [1684us] (51.65%; 99.98%)
+ InferType: 21413us [21413us] (47.88%; 92.71%)
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 ac21be51c6..307baeeeac 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 53.126945 ms
+ Convolution: 53.545089 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 884bdb9ad5..6a4e110a2d 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -598,7 +598,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 11.840041 ms
+ conv2d with tensor core: 12.243044 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 fb07cb9d2f..6c46e3b08f 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -134,8 +134,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.016620
- Baseline: 3.385342
+ Numpy running time: 0.017691
+ Baseline: 3.412250
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.296053
+ Opt1: 0.291376
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.332443
+ Opt2: 0.326029
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114155
+ Opt3: 0.117350
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.107448
+ Opt4: 0.110147
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.102262
+ Opt5: 0.110723
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.134265
+ Opt6: 0.146654
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 40e9b07b51..5b1512db80 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.142** total execution time for **how_to_optimize_operators** files:
+**00:35.082** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.170 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.079 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.873 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.866 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.137 | 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 0e0004a679..f90a9e0874 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
=================
-**09:57.586** total execution time for **how_to_tune_with_autoscheduler** files:
+**10:11.065** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:05.927 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:15.276 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:41.092 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:41.979 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:10.523 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:10.781 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:32.605 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:35.466 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:13.975 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.083 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.464 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.480 | 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 ef725504eb..24488ad8f3 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -243,64 +243,423 @@ cooperative fetching, unrolling and operator fusion.
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- blockIdx_x = T.launch_thread("blockIdx.x", 128)
- conv2d_nchw = T.allocate([4], "float32", "local")
- pad_temp_shared = T.allocate([3136], "float32", "shared")
- kernel_shared = T.allocate([256], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 49)
- conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
+ blockIdx_x = T.launch_thread("blockIdx.x", 224)
+ conv2d_nchw = T.allocate([2], "float32", "local")
+ pad_temp_shared = T.allocate([144], "float32", "shared")
+ kernel_shared = T.allocate([768], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 56)
+ conv2d_nchw_1 = T.Buffer((2,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- for rc_outer_outer, ry_outer_outer, rx_outer_outer in T.grid(8, 3, 3):
- cse_var_2: T.int32 = rc_outer_outer * 576
- cse_var_1: T.int32 = ry_outer_outer * 3
- pad_temp_shared_1 = T.Buffer((3136,), data=pad_temp_shared, scope="shared")
- for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(64):
- cse_var_3: T.int32 = ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49
- threadIdx_x_1 = T.launch_thread("threadIdx.x", 49)
- data_1 = T.Buffer((25088,), data=data.data)
- pad_temp_shared_1[cse_var_3 + threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 // 7 + ry_outer_outer and threadIdx_x_1 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 3136 + cse_var_3 + ry_outer_outer * 7 + rx_outer_outer + threadIdx_x_1 - 8], T.float32(0))
+ for rc_outer_outer in range(32):
+ cse_var_2: T.int32 = rc_outer_outer * 784
+ cse_var_1: T.int32 = rc_outer_outer * 144
threadIdx_x_1 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((256,), data=kernel_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((144,), data=pad_temp_shared, scope="shared")
+ data_1 = T.Buffer((25088,), data=data.data)
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8 and 1 <= blockIdx_x % 7, data_1[cse_var_2 + threadIdx_x_1 // 9 * 49 + threadIdx_x_1 % 9 * 7 + blockIdx_x % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8 and 1 <= blockIdx_x % 7, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 9 * 49 + (threadIdx_x_1 + 2) % 9 * 7 + blockIdx_x % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ if T.likely(threadIdx_x_1 < 32):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8 and 1 <= blockIdx_x % 7, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 9 * 49 + (threadIdx_x_1 + 4) % 9 * 7 + blockIdx_x % 7 - 8], T.float32(0))
+ threadIdx_x_2 = T.env_thread("threadIdx.x")
+ kernel_shared_1 = T.Buffer((768,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x * 18432 + cse_var_2 + threadIdx_x_1 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1 + 49] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 49) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 49) % 64 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1 + 98] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 98) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 34) % 64 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1 + 147] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 147) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 19) % 64 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1 + 196] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 196) // 64 * 4608 + cse_var_2 + threadIdx_x_1 * 9 + cse_var_1 + rx_outer_outer + 36]
- with T.launch_thread(threadIdx_x_1, 49):
- if T.likely(threadIdx_x_1 < 11):
- kernel_shared_1[threadIdx_x_1 + 245] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 245) // 64 * 4608 + cse_var_2 + threadIdx_x_1 * 9 + cse_var_1 + rx_outer_outer + 477]
- for rc_outer_inner in range(16):
- cse_var_4: T.int32 = rc_outer_inner * 4
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x] * kernel_shared_1[cse_var_4]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x] * kernel_shared_1[cse_var_4 + 128]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 49] * kernel_shared_1[cse_var_4 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 49] * kernel_shared_1[cse_var_4 + 129]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 98] * kernel_shared_1[cse_var_4 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 98] * kernel_shared_1[cse_var_4 + 130]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 147] * kernel_shared_1[cse_var_4 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 147] * kernel_shared_1[cse_var_4 + 131]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x] * kernel_shared_1[cse_var_4 + 64]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x] * kernel_shared_1[cse_var_4 + 192]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 49] * kernel_shared_1[cse_var_4 + 65]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 49] * kernel_shared_1[cse_var_4 + 193]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 98] * kernel_shared_1[cse_var_4 + 66]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 98] * kernel_shared_1[cse_var_4 + 194]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 147] * kernel_shared_1[cse_var_4 + 67]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 147] * kernel_shared_1[cse_var_4 + 195]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 56) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 56) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 112) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 112) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 168) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 168) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 224) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 224) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 280) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 280) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 32256]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 392) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 392) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 448) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 448) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 504) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 504) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 560) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 560) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 616) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 616) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 64512]
+ with T.launch_thread(threadIdx_x_2, 56):
+ if T.likely(threadIdx_x_2 < 40):
+ kernel_shared_1[(threadIdx_x_2 + 728) // 48 * 48 + (threadIdx_x_2 + 8) // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 728) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 36]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 42]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 93]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 37]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 43]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 94]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 38]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 44]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 95]
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 49 + threadIdx_x_1 % 9 * 7 + blockIdx_x % 7 - 7], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 9 * 49 + (threadIdx_x_1 + 2) % 9 * 7 + blockIdx_x % 7 - 7], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ if T.likely(threadIdx_x_1 < 32):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 9 * 49 + (threadIdx_x_1 + 4) % 9 * 7 + blockIdx_x % 7 - 7], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 56) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 56) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 112) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 112) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 168) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 168) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 224) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 224) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 280) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 280) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 32257]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 392) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 392) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 448) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 448) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 504) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 504) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 560) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 560) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 616) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 616) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 64513]
+ with T.launch_thread(threadIdx_x_2, 56):
+ if T.likely(threadIdx_x_2 < 40):
+ kernel_shared_1[(threadIdx_x_2 + 728) // 48 * 48 + (threadIdx_x_2 + 8) // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 728) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 36]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 42]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 93]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 37]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 43]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 94]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 38]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 44]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 95]
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8 and blockIdx_x % 7 < 6, data_1[cse_var_2 + threadIdx_x_1 // 9 * 49 + threadIdx_x_1 % 9 * 7 + blockIdx_x % 7 - 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8 and blockIdx_x % 7 < 6, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 9 * 49 + (threadIdx_x_1 + 2) % 9 * 7 + blockIdx_x % 7 - 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ if T.likely(threadIdx_x_1 < 32):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8 and blockIdx_x % 7 < 6, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 9 * 49 + (threadIdx_x_1 + 4) % 9 * 7 + blockIdx_x % 7 - 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 56) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 56) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 112) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 112) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 168) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 168) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 224) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 224) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 280) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 280) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 32258]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 392) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 392) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 448) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 448) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 504) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 504) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 560) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 560) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 616) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 616) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 64514]
+ with T.launch_thread(threadIdx_x_2, 56):
+ if T.likely(threadIdx_x_2 < 40):
+ kernel_shared_1[(threadIdx_x_2 + 728) // 48 * 48 + (threadIdx_x_2 + 8) // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 728) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 36]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 42]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 93]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 37]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 43]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 94]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 38]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 44]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 95]
for i1_inner in range(2):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 196 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 4 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 196 + i1_inner * 49 + threadIdx_x + 98] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 4 + i1_inner + 2], T.float32(0))
+ compute_1[blockIdx_x // 7 * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + blockIdx_x % 7] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x // 7 * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
@@ -350,7 +709,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.308 ms
+ Execution time of this operator: 0.443 ms
@@ -400,20 +759,20 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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=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=1)
- 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_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=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=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_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_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=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
@@ -421,13 +780,13 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
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)
@@ -447,14 +806,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+ 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=56)
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=49)
+ 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=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -479,54 +838,373 @@ 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__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[3136];
- __shared__ float kernel_shared[256];
+ extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[144];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 64; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x))] = (((((1 <= ((((int)threadIdx.x) / 7) + ry_outer_outer)) && (((((int)threadIdx.x) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49)) + (ry_outer_outer * 7)) + rx_outer_outer) + ((int)threadIdx.x)) - 8)] : 0 [...]
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 49) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 49) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 34) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 147) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 19) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 36)];
- if (((int)threadIdx.x) < 11) {
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[(((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 245) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 477)];
- }
- __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 * 196) + ((int)threadIdx.x))] * kernel_shared[(rc_outer_inner * 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 196) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 4) + 128)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 49)] * kernel_shared[((rc_outer_inner * 4) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 49)] * kernel_shared[((rc_outer_inner * 4) + 129)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 98)] * kernel_shared[((rc_outer_inner * 4) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 98)] * kernel_shared[((rc_outer_inner * 4) + 130)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 147)] * kernel_shared[((rc_outer_inner * 4) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 147)] * kernel_shared[((rc_outer_inner * 4) + 131)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 196) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 4) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 196) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 4) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 49)] * kernel_shared[((rc_outer_inner * 4) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 49)] * kernel_shared[((rc_outer_inner * 4) + 193)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 98)] * kernel_shared[((rc_outer_inner * 4) + 66)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 98)] * kernel_shared[((rc_outer_inner * 4) + 194)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 147)] * kernel_shared[((rc_outer_inner * 4) + 67)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 147)] * kernel_shared[((rc_outer_inner * 4) + 195)]));
- }
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) && (1 <= (((int)blockIdx.x) % 7))) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) && (1 <= (((int)blockIdx.x) % 7))) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 9) * 49)) + (((((int)threadIdx.x) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) && (1 <= (((int)blockIdx.x) % 7))) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 9) * 49)) + (((((int)threadIdx.x) + 4) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 56) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 112) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 168) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 224) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 280) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 32256)];
+ kernel_shared[(((((((int)threadIdx.x) + 392) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 504) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 560) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 616) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 64512)];
+ if (((int)threadIdx.x) < 40) {
+ kernel_shared[(((((((int)threadIdx.x) + 728) / 48) * 48) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 9) * 49)) + (((((int)threadIdx.x) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 9) * 49)) + (((((int)threadIdx.x) + 4) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 56) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 112) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 168) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 224) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 280) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 32257)];
+ kernel_shared[(((((((int)threadIdx.x) + 392) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 504) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 560) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 616) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 64513)];
+ if (((int)threadIdx.x) < 40) {
+ kernel_shared[(((((((int)threadIdx.x) + 728) / 48) * 48) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) && ((((int)blockIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) && ((((int)blockIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 9) * 49)) + (((((int)threadIdx.x) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) && ((((int)blockIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 9) * 49)) + (((((int)threadIdx.x) + 4) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 56) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 112) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 168) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 224) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 280) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 32258)];
+ kernel_shared[(((((((int)threadIdx.x) + 392) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 504) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 560) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 616) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 64514)];
+ if (((int)threadIdx.x) < 40) {
+ kernel_shared[(((((((int)threadIdx.x) + 728) / 48) * 48) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -586,7 +1264,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 5.927 seconds)
+ **Total running time of the script:** ( 6 minutes 15.276 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 02fea9fc5c..269f0eeb2e 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.1280 8.1314 8.1316 8.1210 0.0049
+ 8.1472 8.1423 8.1573 8.1418 0.0072
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.523 seconds)
+ **Total running time of the script:** ( 1 minutes 10.781 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 f86bf56e75..878a574fb4 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -666,7 +666,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 739.1851 738.1802 741.9351 737.4398 1.9679
+ 755.4219 755.5400 756.4996 754.2260 0.9319
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 41.092 seconds)
+ **Total running time of the script:** ( 1 minutes 41.979 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 e49eb492a0..50b7e8f958 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -389,10 +389,10 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.Buffer((1024,), data=compute_1)
- for i_inner_init in range(64):
+ for i0_outer_i1_outer_fused in T.parallel(256):
+ compute_1 = T.allocate([256], "float32", "global")
+ compute_2 = T.Buffer((256,), data=compute_1)
+ for i_inner_init in range(16):
cse_var_1: T.int32 = i_inner_init * 16
compute_2[cse_var_1] = T.float32(0)
compute_2[cse_var_1 + 1] = T.float32(0)
@@ -410,7 +410,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
compute_2[cse_var_1 + 13] = T.float32(0)
compute_2[cse_var_1 + 14] = T.float32(0)
compute_2[cse_var_1 + 15] = T.float32(0)
- for elem_idx, i_inner in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i0_outer_i1_outer_fused % 32}), 64):
+ for elem_idx, i_inner in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i0_outer_i1_outer_fused % 32}), 16):
cse_var_2 = T.int32()
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
cse_var_3: T.int32 = i0_outer_i1_outer_fused % 32
@@ -419,54 +419,54 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_4: T.int32 = i_inner * 16
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_5: T.int32 = i_inner * 16 + 1
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_6: T.int32 = i_inner * 16 + 2
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_7: T.int32 = i_inner * 16 + 3
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_8: T.int32 = i_inner * 16 + 4
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_9: T.int32 = i_inner * 16 + 5
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_10: T.int32 = i_inner * 16 + 6
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_11: T.int32 = i_inner * 16 + 7
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_12: T.int32 = i_inner * 16 + 8
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_13: T.int32 = i_inner * 16 + 9
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 9] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 9] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_14: T.int32 = i_inner * 16 + 10
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 10] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 10] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_15: T.int32 = i_inner * 16 + 11
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 11] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 11] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_16: T.int32 = i_inner * 16 + 12
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 12] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 12] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_17: T.int32 = i_inner * 16 + 13
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 13] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 13] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_18: T.int32 = i_inner * 16 + 14
- compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 14] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 14] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_19: T.int32 = i_inner * 16 + 15
- compute_2[cse_var_19] = compute_2[cse_var_19] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 15] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
- for i0_inner in range(64):
- cse_var_20: T.int32 = i0_outer_i1_outer_fused // 32 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
+ compute_2[cse_var_19] = compute_2[cse_var_19] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 15] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner in range(16):
+ cse_var_20: T.int32 = i0_outer_i1_outer_fused // 32 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
compute_3[cse_var_20:cse_var_20 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_20:cse_var_20 + 16], T.Broadcast(T.float32(0), 16))
@@ -519,7 +519,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.697 ms
+ Execution time of this operator: 1.941 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 289d2f2504..6e2d54d4d8 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:44.530** total execution time for **how_to_tune_with_autotvm** files:
+**00:40.987** 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``) | 00:44.496 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:40.953 | 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_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 1f85e5ea6f..a0a4ffd965 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -390,7 +390,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3983708
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6143818
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -513,9 +513,8 @@ 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, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9153411
- No: 3 GFLOPS: 254.83/254.83 result: MeasureResult(costs=(0.0009084488378378379,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.209742546081543, timestamp=1681199202.8271508) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2146868
- No: 4 GFLOPS: 0.00/254.83 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2047328
+ 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
@@ -637,8 +636,9 @@ 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, 1, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,157950
- No: 5 GFLOPS: 0.00/254.83 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9870382
+ No: 4 GFLOPS: 8.10/8.10 result: MeasureResult(costs=(0.02856754475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.651654005050659, timestamp=1681204183.3537586) [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7036804
+ No: 5 GFLOPS: 0.00/8.10 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -760,9 +760,9 @@ 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, 16, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5195763
- No: 6 GFLOPS: 6.95/254.83 result: MeasureResult(costs=(0.0333320655,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.989668369293213, timestamp=1681199210.3548458) [('tile_f', [-1, 16, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8751858
- No: 7 GFLOPS: 0.00/254.83 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3246623
+ No: 6 GFLOPS: 161.97/161.97 result: MeasureResult(costs=(0.0014293008333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9774255752563477, timestamp=1681204186.9771235) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3561056
+ No: 7 GFLOPS: 0.00/161.97 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
@@ -884,11 +884,8 @@ 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, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3451630
- No: 8 GFLOPS: 25.24/254.83 result: MeasureResult(costs=(0.009173023833333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.264514207839966, timestamp=1681199212.786609) [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8959952
- No: 9 GFLOPS: 6.25/254.83 result: MeasureResult(costs=(0.037047798,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.417418956756592, timestamp=1681199215.391768) [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5240643
- No: 10 GFLOPS: 806.76/806.76 result: MeasureResult(costs=(0.00028695028520499103,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.779116153717041, timestamp=1681199216.5159807) [('tile_f', [-1, 1, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9693065
- No: 11 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9439487
+ No: 8 GFLOPS: 0.00/161.97 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
@@ -1010,8 +1007,8 @@ 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, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,124811
- No: 12 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10008720
+ No: 9 GFLOPS: 0.00/161.97 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
@@ -1133,8 +1130,8 @@ 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, 1, 512]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,904859
- No: 13 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3047483
+ No: 10 GFLOPS: 0.00/161.97 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
@@ -1256,11 +1253,8 @@ 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, 16, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7122399
- No: 14 GFLOPS: 18.23/806.76 result: MeasureResult(costs=(0.012698629181818182,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.832524061203003, timestamp=1681199220.1907861) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6509154
- No: 15 GFLOPS: 1.64/806.76 result: MeasureResult(costs=(0.14085453774999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.732933044433594, timestamp=1681199222.5791147) [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3915984
- No: 16 GFLOPS: 48.07/806.76 result: MeasureResult(costs=(0.004815445285714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2162880897521973, timestamp=1681199223.4586391) [('tile_f', [-1, 4, 2, 1]), ('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, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6393432
- No: 17 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6953672
+ No: 11 GFLOPS: 0.00/161.97 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
@@ -1382,9 +1376,8 @@ 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, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3031186
- No: 18 GFLOPS: 156.70/806.76 result: MeasureResult(costs=(0.001477364425925926,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9475483894348145, timestamp=1681199225.576632) [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3562995
- No: 19 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2883749
+ No: 12 GFLOPS: 0.00/161.97 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
@@ -1506,8 +1499,8 @@ 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, 512, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2606614
- No: 20 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10205865
+ No: 13 GFLOPS: 0.00/161.97 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
@@ -1629,7 +1622,502 @@ 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, 16, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10436364
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6507423
+ No: 14 GFLOPS: 0.00/161.97 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2965851
+ No: 15 GFLOPS: 0.00/161.97 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8194189
+ No: 16 GFLOPS: 0.00/161.97 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,700279
+ No: 17 GFLOPS: 7.84/161.97 result: MeasureResult(costs=(0.029516136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.433065414428711, timestamp=1681204194.00447) [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8555605
+ No: 18 GFLOPS: 0.00/161.97 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+ tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+ Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2959382
+ No: 19 GFLOPS: 141.09/161.97 result: MeasureResult(costs=(0.0016408140204081634,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5441296100616455, timestamp=1681204195.0882215) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1767376
+ No: 20 GFLOPS: 175.13/175.13 result: MeasureResult(costs=(0.0013218766184210525,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.734405040740967, timestamp=1681204195.9468648) [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3631496
@@ -1684,9 +2172,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9693065
+ [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3631496
Finish loading 20 records
- Time cost of this operator: 0.000574
+ Time cost of this operator: 0.001668
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 c39833eca6..873485e516 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -360,10 +360,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.7 98.725 (1, 2, 10, 10, 3) 2 1 [315.7]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.096 0.968 (1, 6, 10, 10) 1 1 [3.096]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.982 0.307 (1, 1, 10, 10, 3) 1 1 [0.982]
- Total_time - 319.779 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.9 98.745 (1, 2, 10, 10, 3) 2 1 [315.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.063 0.957 (1, 6, 10, 10) 1 1 [3.063]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.297 (1, 1, 10, 10, 3) 1 1 [0.952]
+ Total_time - 319.914 - - - - -
@@ -428,10 +428,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.3 97.346 (1, 6, 10, 10, 1) 2 1 [100.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.762 1.71 (1, 6, 10, 10) 1 1 [1.762]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.944 (1, 1, 10, 10, 3) 1 1 [0.973]
- Total_time - 103.035 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.4 97.328 (1, 6, 10, 10, 1) 2 1 [100.4]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.788 1.733 (1, 6, 10, 10) 1 1 [1.788]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.938 (1, 1, 10, 10, 3) 1 1 [0.968]
+ Total_time - 103.156 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 25.374 seconds)
+ **Total running time of the script:** ( 1 minutes 22.622 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_autotune.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
index 56d30d6bc2..5353ff1139 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -118,7 +118,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
66%|######6 | 2.27M/3.42M [00:00<00:00, 23.8MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 34.2MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 214MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 17.055 seconds)
+ **Total running time of the script:** ( 1 minutes 17.488 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_pytorch.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index ecf47ea1d9..ca783422ee 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -217,7 +217,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpom9tipxn/images/random'
+ '/tmp/tmp9ri8kf_i/images/random'
@@ -308,7 +308,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0]
+ :alt: [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -317,8 +317,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpom9tipxn/images/target contains 8144 images
- /tmp/tmpom9tipxn/images/random contains 5000 images
+ /tmp/tmp9ri8kf_i/images/target contains 8144 images
+ /tmp/tmp9ri8kf_i/images/random contains 5000 images
@@ -493,13 +493,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 41s - loss: 0.2213 - accuracy: 0.9217 - val_loss: 0.1229 - val_accuracy: 0.9558 - 41s/epoch - 126ms/step
+ 328/328 - 42s - loss: 0.2122 - accuracy: 0.9251 - val_loss: 0.1189 - val_accuracy: 0.9581 - 42s/epoch - 127ms/step
Epoch 2/3
- 328/328 - 35s - loss: 0.1059 - accuracy: 0.9599 - val_loss: 0.1022 - val_accuracy: 0.9600 - 35s/epoch - 106ms/step
+ 328/328 - 35s - loss: 0.0902 - accuracy: 0.9659 - val_loss: 0.1105 - val_accuracy: 0.9679 - 35s/epoch - 106ms/step
Epoch 3/3
- 328/328 - 35s - loss: 0.0564 - accuracy: 0.9798 - val_loss: 0.1119 - val_accuracy: 0.9611 - 35s/epoch - 105ms/step
+ 328/328 - 34s - loss: 0.0678 - accuracy: 0.9746 - val_loss: 0.1039 - val_accuracy: 0.9694 - 34s/epoch - 105ms/step
- <keras.callbacks.History object at 0x7f6219312c50>
+ <keras.callbacks.History object at 0x7f7e4d3b4810>
@@ -860,7 +860,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 21.025 seconds)
+ **Total running time of the script:** ( 4 minutes 32.350 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 573829a760..d0937305f4 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
Computation times
=================
-**07:29.102** total execution time for **how_to_work_with_microtvm** files:
+**07:37.937** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:21.025 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:32.350 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:25.374 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:22.622 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:17.055 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:17.488 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.256 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.199 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:08.043 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:07.774 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.350 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.504 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index c171d74ff7..cc762cc00b 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
=================
-**00:36.265** total execution time for **how_to_work_with_relay** files:
+**00:36.373** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.765 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.901 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:02.853 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:02.851 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.641 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.614 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 31029bb070..10d368f17d 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
@@ -278,7 +278,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f5e6246d3b0>
+ <function my_cuda_math_rule at 0x7f7be3a87200>
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 96a0f149a6..cb080e3567 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
=================
-**00:08.760** total execution time for **how_to_work_with_schedules** files:
+**00:08.908** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.077 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.161 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.190 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.252 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.619 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.616 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.601 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.127 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.130 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.062 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.063 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.055 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.030 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.029 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 8ec6906701..2c4afa9191 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:31.761** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:30.760** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.754 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:30.753 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index dd4dfa1ad8..293a198c3a 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 34.14s!
+ resnet18_v1 inference graph built in 32.77s!
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 fd8425472a..16b4737dfd 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 22.95s!
+ yolov3-tiny inference graph built in 22.39s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index dde641b65a..4d6ee0c319 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:41.356** total execution time for **topic_vta_tutorials_frontend** files:
+**01:39.289** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:51.028 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.743 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.328 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.546 | 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 bdeb74197b..fd889e9ad5 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
=================
-**00:03.234** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.203** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.745 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.728 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.489 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.475 | 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 5c87c5d6aa..8a9a7f528c 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
=================
-**00:00.828** total execution time for **topic_vta_tutorials** files:
+**00:00.816** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.429 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.421 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.399 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.395 | 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 7d8ffe2315..303381f0ab 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,6 +207,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ *E
+
+
@@ -318,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 98.360 ms
+ Execution time of this operator: 93.781 ms
@@ -434,7 +441,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 27.679 seconds)
+ **Total running time of the script:** ( 1 minutes 36.897 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 6215a24639..fc27c8ec45 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -454,16 +454,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 11.06/11.06 result: MeasureResult(costs=(0.024268704999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6355149745941162, timestamp=1681197560.3814583) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
- No: 2 GFLOPS: 3.22/11.06 result: MeasureResult(costs=(0.0834299428,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.581608772277832, timestamp=1681197563.2382274) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
- No: 3 GFLOPS: 12.54/12.54 result: MeasureResult(costs=(0.0214062574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6045653820037842, timestamp=1681197565.1039245) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
- No: 4 GFLOPS: 1.51/12.54 result: MeasureResult(costs=(0.17822883260000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.060458183288574, timestamp=1681197568.2109227) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
- No: 5 GFLOPS: 3.88/12.54 result: MeasureResult(costs=(0.0692695088,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.362046480178833, timestamp=1681197569.6863804) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
- No: 6 GFLOPS: 11.35/12.54 result: MeasureResult(costs=(0.0236502174,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6270618438720703, timestamp=1681197570.331723) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
- No: 7 GFLOPS: 3.79/12.54 result: MeasureResult(costs=(0.0707499488,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3853721618652344, timestamp=1681197573.0042627) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
- No: 8 GFLOPS: 3.07/12.54 result: MeasureResult(costs=(0.08754015000000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6451199054718018, timestamp=1681197574.6616476) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
- No: 9 GFLOPS: 11.16/12.54 result: MeasureResult(costs=(0.024050462,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6092183589935303, timestamp=1681197575.3859806) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
- No: 10 GFLOPS: 3.02/12.54 result: MeasureResult(costs=(0.0887491358,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6393957138061523, timestamp=1681197577.0684767) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 1.52/1.52 result: MeasureResult(costs=(0.17712990560000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.088336229324341, timestamp=1681202515.178741) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+ No: 2 GFLOPS: 12.85/12.85 result: MeasureResult(costs=(0.0208879486,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6977832317352295, timestamp=1681202515.7725067) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+ No: 3 GFLOPS: 3.33/12.85 result: MeasureResult(costs=(0.08067693719999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.551457166671753, timestamp=1681202518.5617752) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
+ No: 4 GFLOPS: 0.88/12.85 result: MeasureResult(costs=(0.3056937464,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.128290176391602, timestamp=1681202523.7079847) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+ No: 5 GFLOPS: 1.50/12.85 result: MeasureResult(costs=(0.1786422818,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1030025482177734, timestamp=1681202526.9487379) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+ No: 6 GFLOPS: 0.51/12.85 result: MeasureResult(costs=(0.5311725566,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.755533218383789, timestamp=1681202536.9443994) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
+ No: 7 GFLOPS: 11.78/12.85 result: MeasureResult(costs=(0.022787891400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6363482475280762, timestamp=1681202538.8158693) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
+ No: 8 GFLOPS: 4.53/12.85 result: MeasureResult(costs=(0.059290734,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2143659591674805, timestamp=1681202540.0241356) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
+ No: 9 GFLOPS: 3.06/12.85 result: MeasureResult(costs=(0.08760568839999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6502587795257568, timestamp=1681202541.7958884) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+ No: 10 GFLOPS: 11.72/12.85 result: MeasureResult(costs=(0.022899041399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6210606098175049, timestamp=1681202542.4202776) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index b73d429415..9793a4db07 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -311,7 +311,7 @@ standard deviation.
.. code-block:: none
- {'mean': 485.39099493000094, 'median': 485.2391821500021, 'std': 1.1640439743505182}
+ {'mean': 508.9282783900012, 'median': 509.54074805000573, 'std': 1.5907018118433454}
@@ -545,31 +545,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 21.72/ 21.72 GFLOPS | Progress: (4/20) | 10.98 s
[Task 1/25] Current/Best: 9.44/ 21.89 GFLOPS | Progress: (8/20) | 15.79 s
[Task 1/25] Current/Best: 9.45/ 21.89 GFLOPS | Progress: (12/20) | 17.97 s
[Task 1/25] Current/Best: 7.02/ 23.77 GFLOPS | Progress: (16/20) | 20.00 s
[Task 1/25] Current/Best: 5.75/ 23.77 GFLOPS | Progress: (20/20) | 22.42 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 3.17/ 20.34 GFLOPS | Progress: (4/20) | 4.19 s
[Task 2/25] Current/Best: 18.43/ 20.77 GFLOPS | Progress: (8/20) | 6.25 s
[Task 2/25] Current/Best: 7.48/ 20.77 GFLOPS | Progress: (12/20) | 8.23 s
[Task 2/25] Current/Best: 19.59/ 20.77 GFLOPS | Progress: (16/20) | 9.88 s
[Task 2/25] Current/Best: 15.72/ 20.77 GFLOPS | Progress: (20/20) | 11.86 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 23.74/ 23.74 GFLOPS | Progress: (4/20) | 4.98 s
[Task 3/25] Current/Best: 6.32/ 24.68 GFLOPS | Progress: (8/20) | 7.73 s
[Task 3/25] Current/Best: 14.68/ 24.68 GFLOPS | Progress: (12/20) | 9.98 s
[Task 3/25] Current/Best: 22.55/ 24.68 GFLOPS | Progress: (16/20) | 12.85 s
[Task 3/25] Current/Best: 7.97/ 24.68 GFLOPS | Progress: (20/20) | 15.24 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.94/ 16.21 GFLOPS | Progress: (4/20) | 7.57 s
[Task 4/25] Current/Best: 11.11/ 22.87 GFLOPS | Progress: (8/20) | 9.16 s
[Task 4/25] Current/Best: 10.29/ 22.87 GFLOPS | Progress: (12/20) | 20.33 s
[Task 4/25] Current/Best: 9.19/ 22.87 GFLOPS | Progress: (16/20) | 28.04 s
[Task 4/25] Current/Best: 10.18/ 22.87 GFLOPS | Progress: (20/20) | 30.18 s
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 20.89/ 20.89 GFLOPS | Progress: (4/20) | 5.42 s
[Task 5/25] Current/Best: 18.14/ 20.89 GFLOPS | Progress: (8/20) | 7.22 s
[Task 5/25] Current/Best: 14.07/ 20.89 GFLOPS | Progress: (12/20) | 10.99 s
[Task 5/25] Current/Best: 3.99/ 20.89 GFLOPS | Progress: (16/20) | 13.35 s
[Task 5/25] Current/Best: 14.16/ 20.89 GFLOPS | Progress: (20/20
) | 15.31 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 11.97/ 17.90 GFLOPS | Progress: (4/20) | 5.13 s
[Task 6/25] Current/Best: 14.49/ 17.90 GFLOPS | Progress: (8/20) | 8.36 s
[Task 6/25] Current/Best: 16.44/ 17.90 GFLOPS | Progress: (12/20) | 11.57 s
[Task 6/25] Current/Best: 7.31/ 17.90 GFLOPS | Progress: (16/20) | 14.51 s Done.
-
[Task 6/25] Current/Best: 12.24/ 17.90 GFLOPS | Progress: (20/20) | 17.19 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 6.31/ 14.75 GFLOPS | Progress: (4/20) | 5.55 s
[Task 7/25] Current/Best: 12.23/ 16.49 GFLOPS | Progress: (8/20) | 8.53 s
[Task 7/25] Current/Best: 13.25/ 22.42 GFLOPS | Progress: (12/20) | 10.99 s
[Task 7/25] Current/Best: 15.87/ 22.42 GFLOPS | Progress: (16/20) | 13.40 s
[Task 7/25] Current/Best: 3.10/ 22.42 GFLOPS | Progress: (20/20) | 16.38 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.83/ 17.98 GFLOPS | Progress: (4/20) | 5.41 s
[Task 8/25] Current/Best: 12.81/ 17.98 GFLOPS | Progress: (8/20) | 8.41 s
[Task 8/25] Current/Best: 13.09/ 17.98 GFLOPS | Progress: (12/20) | 11.01 s
[Task 8/25] Current/Best: 10.49/ 21.30 GFLOPS | Progress: (16/20) | 13.06 s
[Task 8/25] Current/Best: 6.39/ 21.30 GFLOPS | Progress: (20/20) | 16.51 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 12.80/ 21.22 GFLOPS | Progress: (4/20) | 4.37 s
[Task 9/25] Current/Best: 21.42/ 21.42 GFLOPS | Progress: (8/20) | 6.28 s
[Task 9/25] Current/Best: 18.08/ 21.42 GFLOPS | Progress: (12/20) | 11.42 s
[Task 9/25] Current/Best: 11.26/ 21.42 GFLOPS | Progress: (16/20) | 14.47 s
[Task 9/25] Current/Best: 20.29/ 21.44 GFLOPS | Progress: (20/20) | 16.08 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 10.28/ 18.02 GFLOPS | Progress: (4/20) | 5.28 s
[Task 10/25] Current/Best: 21.55/ 21.55 GFLOPS | Progress: (8/20) | 7.01 s
[Task 10/25] Current/Best: 16.53/ 21.55 GFLOPS | Progress: (12/20) | 9.20 s
[Task 10/25] Current/Best: 19.73/ 21.55 GFLOPS | Progress: (16/20) | 12.88 s
[Task 10/25] Current/Best: 7.71/ 21.55 GFLOPS | Progress: (20/20) | 14.59 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 19.51/ 20.45 GFLOPS | Progress: (4/20) | 5.01 s
[Task 11/25] Current/Best: 14.46/ 20.45 GFLOPS | Progress: (8/20) | 8.14 s
[Task 11/25] Current/Best: 18.90/ 20.45 GFLOPS | Progress: (12/20) | 10.99 s
[Task 11/25] Current/Best: 17.15/ 21.64 GFLOPS | Progress: (16/20) | 13.45 s
[Task 11/25] Current/Best: 22.19/ 22.19 GFLOPS | Progress: (20/20) | 16.39 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 12.92/ 21.79 GFLOPS | Progress: (4/20) | 5.19 s
[Task 12/25] Current/Best: 13.48/ 21.79 GFLOPS | Progress: (8/20) | 8.80 s
[Task 12/25] Current/Best: 5.06/ 21.79 GFLOPS | Progress: (12/20) | 13.65 s
[Task 12/25] Current/Best: 12.05/ 21.79 GFLOPS | Progress: (16/20) | 17.64 s
[Task 12/25] Current/Best: 8.50/ 21.79 GFLOPS | Progress: (20/20) | 20.69 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 15.49/ 15.49 GFLOPS | Progress: (4/20) | 5.96 s
[Task 13/25] Current/Best: 9.09/ 15.49 GFLOPS | Progress: (8/20) | 8.59 s
[Task 13/25] Current/Best: 17.69/ 17.69 GFLOPS | Progress: (12/20) | 12.09 s
[Task 13/25] Current/Best: 16.68/ 18.59 GFLOPS | Progress: (16/20) | 15.99 s
[Task 13/25] Current/Best: 16.62/ 18.59 GFLOPS | Progress: (20/20) | 18.79 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 15.52/ 16.31 GFLOPS | Progress: (4/20) | 6.39 s
[Task 14/25] Current/Best: 15.35/ 16.31 GFLOPS | Progress: (8/20) | 8.88 s
[Task 14/25] Current/Best: 15.48/ 16.31 GFLOPS | Progress: (12/20) | 13.87 s
[Task 14/25] Current/Best: 10.52/ 16.31 GFLOPS | Progress: (16/20) | 17.78 s
[Task 14/25] Current/Best: 10.11/ 18.18 GFLOPS | Progress: (20/20) | 19.95 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.37/ 19.99 GFLOPS | Progress: (4/20) | 6.36 s
[Task 15/25] Current/Best: 12.58/ 19.99 GFLOPS | Progress: (8/20) | 9.20 s
[Task 15/25] Current/Best: 15.57/ 20.30 GFLOPS | Progress: (12/20) | 11.21 s
[Task 15/25] Current/Best: 18.69/ 20.30 GFLOPS | Progress: (16/20) | 12.80 s
[Task 15/25] Current/Best: 18.69/ 20.30 GFLOPS | Progress: (20/20
) | 15.10 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 9.61/ 17.76 GFLOPS | Progress: (4/20) | 4.86 s
[Task 16/25] Current/Best: 19.04/ 19.87 GFLOPS | Progress: (8/20) | 7.92 s
[Task 16/25] Current/Best: 4.34/ 19.87 GFLOPS | Progress: (12/20) | 9.75 s
[Task 16/25] Current/Best: 5.19/ 19.87 GFLOPS | Progress: (16/20) | 11.53 s
[Task 16/25] Current/Best: 17.90/ 19.87 GFLOPS | Progress: (20/20) | 13.25 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 21.49/ 21.49 GFLOPS | Progress: (4/20) | 5.04 s
[Task 17/25] Current/Best: 10.14/ 21.49 GFLOPS | Progress: (8/20) | 7.52 s
[Task 17/25] Current/Best: 12.90/ 21.49 GFLOPS | Progress: (12/20) | 10.22 s
[Task 17/25] Current/Best: 9.88/ 21.49 GFLOPS | Progress: (16/20) | 12.69 s
[Task 17/25] Current/Best: 16.10/ 21.49 GFLOPS | Progress: (20/20) | 15.52 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (4/20) | 4.73 s
[Task 18/25] Current/Best: 10.87/ 20.26 GFLOPS | Progress: (8/20) | 7.30 s
[Task 18/25] Current/Best: 11.91/ 20.26 GFLOPS | Progress: (12/20) | 9.89 s
[Task 18/25] Current/Best: 12.33/ 20.26 GFLOPS | Progress: (16/20) | 13.57 s
[Task 18/25] Current/Best: 18.21/ 20.26 GFLOPS | Progress: (20/20) | 15.84 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 18.06/ 18.14 GFLOPS | Progress: (4/20) | 6.16 s
[Task 19/25] Current/Best: 9.36/ 18.14 GFLOPS | Progress: (8/20) | 9.93 s
[Task 19/25] Current/Best: 8.66/ 18.48 GFLOPS | Progress: (12/20) | 12.96 s
[Task 19/25] Current/Best: 4.76/ 22.29 GFLOPS | Progress: (16/20) | 18.15 s
[Task 19/25] Current/Best: 10.59/ 22.29 GFLOPS | Progress: (20/20) | 21.97 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 16.96/ 20.79 GFLOPS | Progress: (4/20) | 5.34 s
[Task 20/25] Current/Best: 5.37/ 20.79 GFLOPS | Progress: (8/20) | 9.07 s
[Task 20/25] Current/Best: 14.04/ 20.79 GFLOPS | Progress: (12/20) | 11.34 s
[Task 20/25] Current/Best: 18.80/ 20.79 GFLOPS | Progress: (16/20) | 13.50 s
[Task 20/25] Current/Best: 13.99/ 20.79 GFLOPS | Progress: (20/20) | 16.72 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 8.34/ 23.16 GFLOPS | Progress: (4/20) | 10.93 s
[Task 1/25] Current/Best: 3.19/ 23.16 GFLOPS | Progress: (8/20) | 15.25 s
[Task 1/25] Current/Best: 7.07/ 23.16 GFLOPS | Progress: (12/20) | 20.74 s
[Task 1/25] Current/Best: 14.14/ 23.16 GFLOPS | Progress: (16/20) | 24.75 s
[Task 1/25] Current/Best: 16.88/ 23.79 GFLOPS | Progress: (20/20) | 27.46 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 16.17/ 16.97 GFLOPS | Progress: (4/20) | 4.38 s
[Task 2/25] Current/Best: 13.04/ 16.97 GFLOPS | Progress: (8/20) | 6.44 s
[Task 2/25] Current/Best: 22.07/ 22.07 GFLOPS | Progress: (12/20) | 8.40 s
[Task 2/25] Current/Best: 6.12/ 22.07 GFLOPS | Progress: (16/20) | 10.38 s
[Task 2/25] Current/Best: 5.47/ 22.07 GFLOPS | Progress: (20/20) | 11.97 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.20/ 14.36 GFLOPS | Progress: (4/20) | 5.38 s
[Task 3/25] Current/Best: 12.53/ 20.22 GFLOPS | Progress: (8/20) | 9.61 s
[Task 3/25] Current/Best: 8.43/ 20.22 GFLOPS | Progress: (12/20) | 12.18 s
[Task 3/25] Current/Best: 17.25/ 20.22 GFLOPS | Progress: (16/20) | 14.88 s
[Task 3/25] Current/Best: 8.41/ 20.22 GFLOPS | Progress: (20/20) | 17.46 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 15.59/ 15.59 GFLOPS | Progress: (4/20) | 4.82 s
[Task 4/25] Current/Best: 8.55/ 16.22 GFLOPS | Progress: (8/20) | 9.98 s
[Task 4/25] Current/Best: 15.06/ 16.22 GFLOPS | Progress: (12/20) | 12.10 s
[Task 4/25] Current/Best: 17.46/ 22.81 GFLOPS | Progress: (16/20) | 16.29 s
[Task 4/25] Current/Best: 13.21/ 22.81 GFLOPS | Progress: (20/20) | 18.88 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 19.44/ 23.25 GFLOPS | Progress: (4/20) | 4.34 s
[Task 5/25] Current/Best: 21.13/ 23.25 GFLOPS | Progress: (8/20) | 6.30 s
[Task 5/25] Current/Best: 3.02/ 23.25 GFLOPS | Progress: (12/20) | 9.08 s
[Task 5/25] Current/Best: 15.83/ 23.25 GFLOPS | Progress: (16/20) | 11.63 s
[Task 5/25] Current/Best: 18.04/ 23.25 GFLOPS | Progress: (20/20) | 13.71 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 11.17/ 14.49 GFLOPS | Progress: (4/20) | 5.19 s
[Task 6/25] Current/Best: 8.76/ 14.49 GFLOPS | Progress: (8/20) | 8.03 s
[Task 6/25] Current/Best: 14.73/ 17.87 GFLOPS | Progress: (12/20) | 10.71 s
[Task 6/25] Current/Best: 12.98/ 17.87 GFLOPS | Progress: (16/20) | 12.81 s
[Task 6/25] Current/Best: 9.61/ 17.87 GFLOPS | Progress: (20/20) | 19.52 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.75/ 15.75 GFLOPS | Progress: (4/20) | 5.77 s
[Task 7/25] Current/Best: 5.77/ 15.75 GFLOPS | Progress: (8/20) | 8.79 s
[Task 7/25] Current/Best: 7.16/ 17.87 GFLOPS | Progress: (12/20) | 11.38 s
[Task 7/25] Current/Best: 12.28/ 18.17 GFLOPS | Progress: (16/20) | 14.26 s
[Task 7/25] Current/Best: 14.73/ 19.94 GFLOPS | Progress: (20/20) | 16.46 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 13.81/ 13.93 GFLOPS | Progress: (4/20) | 5.40 s
[Task 8/25] Current/Best: 13.00/ 13.93 GFLOPS | Progress: (8/20) | 10.14 s
[Task 8/25] Current/Best: 14.84/ 14.84 GFLOPS | Progress: (12/20) | 21.83 s
[Task 8/25] Current/Best: 4.96/ 16.07 GFLOPS | Progress: (16/20) | 30.54 s
[Task 8/25] Current/Best: 2.70/ 16.07 GFLOPS | Progress: (20/20) | 34.28 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 5.43/ 12.18 GFLOPS | Progress: (4/20) | 5.20 s
[Task 9/25] Current/Best: 11.07/ 16.51 GFLOPS | Progress: (8/20) | 10.82 s
[Task 9/25] Current/Best: 13.99/ 23.03 GFLOPS | Progress: (12/20) | 12.85 s
[Task 9/25] Current/Best: 17.58/ 23.03 GFLOPS | Progress: (16/20) | 17.69 s
[Task 9/25] Current/Best: 3.24/ 23.03 GFLOPS | Progress: (20/20) | 21.82 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 13.26/ 18.93 GFLOPS | Progress: (4/20) | 5.15 s
[Task 10/25] Current/Best: 14.07/ 18.93 GFLOPS | Progress: (8/20) | 8.34 s
[Task 10/25] Current/Best: 8.07/ 18.93 GFLOPS | Progress: (12/20) | 10.42 s
[Task 10/25] Current/Best: 15.59/ 18.93 GFLOPS | Progress: (16/20) | 12.49 s
[Task 10/25] Current/Best: 2.51/ 18.93 GFLOPS | Progress: (20/20) | 14.47 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 7.81/ 23.18 GFLOPS | Progress: (4/20) | 6.25 s
[Task 11/25] Current/Best: 14.57/ 23.18 GFLOPS | Progress: (8/20) | 8.81 s
[Task 11/25] Current/Best: 17.56/ 23.18 GFLOPS | Progress: (12/20) | 11.82 s
[Task 11/25] Current/Best: 7.04/ 23.18 GFLOPS | Progress: (16/20) | 14.60 s
[Task 11/25] Current/Best: 12.87/ 23.18 GFLOPS | Progress: (20/20) | 17.18 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 4.45/ 12.60 GFLOPS | Progress: (4/20) | 6.53 s
[Task 12/25] Current/Best: 14.27/ 20.89 GFLOPS | Progress: (8/20) | 8.58 s
[Task 12/25] Current/Best: 10.13/ 20.89 GFLOPS | Progress: (12/20) | 12.05 s
[Task 12/25] Current/Best: 13.98/ 20.89 GFLOPS | Progress: (16/20) | 14.50 s
[Task 12/25] Current/Best: 9.12/ 22.12 GFLOPS | Progress: (20/20) | 18.54 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 11.46/ 12.10 GFLOPS | Progress: (4/20) | 6.94 s
[Task 13/25] Current/Best: 17.75/ 17.75 GFLOPS | Progress: (8/20) | 9.26 s
[Task 13/25] Current/Best: 14.14/ 22.81 GFLOPS | Progress: (12/20) | 11.35 s
[Task 13/25] Current/Best: 17.22/ 22.81 GFLOPS | Progress: (16/20) | 14.27 s
[Task 13/25] Current/Best: 15.04/ 22.81 GFLOPS | Progress: (20/20) | 16.54 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 14.20/ 14.20 GFLOPS | Progress: (4/20) | 5.48 s
[Task 14/25] Current/Best: 13.27/ 14.20 GFLOPS | Progress: (8/20) | 11.16 s
[Task 14/25] Current/Best: 12.96/ 14.48 GFLOPS | Progress: (12/20) | 12.87 s
[Task 14/25] Current/Best: 18.40/ 18.40 GFLOPS | Progress: (16/20) | 16.50 s
[Task 14/25] Current/Best: 11.00/ 18.40 GFLOPS | Progress: (20/20) | 20.07 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 15/25] Current/Best: 12.06/ 21.20 GFLOPS | Progress: (4/20) | 7.09 s
[Task 15/25] Current/Best: 6.37/ 21.20 GFLOPS | Progress: (8/20) | 9.95 s
[Task 15/25] Current/Best: 12.88/ 21.20 GFLOPS | Progress: (12/20) | 11.82 s
[Task 15/25] Current/Best: 9.56/ 21.20 GFLOPS | Progress: (16/20) | 15.46 s
[Task 15/25] Current/Best: 9.82/ 21.20 GFLOPS | Progress: (20/20) | 18.15 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.24/ 19.24 GFLOPS | Progress: (4/20) | 4.82 s
[Task 16/25] Current/Best: 15.64/ 19.24 GFLOPS | Progress: (8/20) | 6.60 s
[Task 16/25] Current/Best: 9.11/ 19.24 GFLOPS | Progress: (12/20) | 8.92 s
[Task 16/25] Current/Best: 13.74/ 19.95 GFLOPS | Progress: (16/20) | 10.71 s
[Task 16/25] Current/Best: 9.30/ 19.95 GFLOPS | Progress: (20/20) | 12.27 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.82/ 22.48 GFLOPS | Progress: (4/20) | 4.91 s
[Task 17/25] Current/Best: 6.11/ 22.48 GFLOPS | Progress: (8/20) | 7.96 s
[Task 17/25] Current/Best: 11.70/ 22.48 GFLOPS | Progress: (12/20) | 10.54 s
[Task 17/25] Current/Best: 19.60/ 22.48 GFLOPS | Progress: (16/20) | 12.80 s
[Task 17/25] Current/Best: 7.00/ 23.20 GFLOPS | Progress: (20/20) | 15.80 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 15.02/ 19.13 GFLOPS | Progress: (4/20) | 6.11 s
[Task 18/25] Current/Best: 16.20/ 20.33 GFLOPS | Progress: (8/20) | 8.32 s
[Task 18/25] Current/Best: 15.35/ 21.15 GFLOPS | Progress: (12/20) | 10.86 s
[Task 18/25] Current/Best: 7.02/ 21.15 GFLOPS | Progress: (16/20) | 14.61 s
[Task 18/25] Current/Best: 10.44/ 21.15 GFLOPS | Progress: (20/20) | 17.97 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.86/ 11.86 GFLOPS | Progress: (4/20) | 5.93 s
[Task 19/25] Current/Best: 7.40/ 17.02 GFLOPS | Progress: (8/20) | 8.95 s
[Task 19/25] Current/Best: 10.72/ 19.65 GFLOPS | Progress: (12/20) | 11.63 s
[Task 19/25] Current/Best: 11.09/ 19.65 GFLOPS | Progress: (16/20) | 15.17 s
[Task 19/25] Current/Best: 15.56/ 19.65 GFLOPS | Progress: (20/20) | 18.84 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.67/ 19.88 GFLOPS | Progress: (4/20) | 4.77 s
[Task 20/25] Current/Best: 16.47/ 19.88 GFLOPS | Progress: (8/20) | 8.01 s
[Task 20/25] Current/Best: 6.20/ 19.88 GFLOPS | Progress: (12/20) | 11.20 s
[Task 20/25] Current/Best: 16.93/ 19.88 GFLOPS | Progress: (16/20) | 14.57 s
[Task 20/25] Current/Best: 16.94/ 19.88 GFLOPS | Progress: (20/20) | 17.39 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 21/25] Current/Best: 14.48/ 14.48 GFLOPS | Progress: (4/20) | 5.62 s
[Task 21/25] Current/Best: 9.28/ 14.48 GFLOPS | Progress: (8/20) | 8.62 s
[Task 21/25] Current/Best: 15.96/ 17.99 GFLOPS | Progress: (12/20) | 11.08 s
[Task 21/25] Current/Best: 18.70/ 18.70 GFLOPS | Progress: (16/20) | 13.90 s
[Task 21/25] Current/Best: 18.13/ 19.65 GFLOPS | Progress: (20/20) | 17.40 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 7.49 GFLOPS | Progress: (4/20) | 5.26 s
[Task 22/25] Current/Best: 17.82/ 19.95 GFLOPS | Progress: (8/20) | 7.01 s
[Task 22/25] Current/Best: 10.67/ 19.95 GFLOPS | Progress: (12/20) | 8.75 s
[Task 22/25] Current/Best: 17.76/ 23.01 GFLOPS | Progress: (16/20) | 10.48 s
[Task 22/25] Current/Best: 13.74/ 23.01 GFLOPS | Progress: (20/20) | 12.80 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 8.82/ 23.47 GFLOPS | Progress: (4/20) | 5.90 s
[Task 23/25] Current/Best: 1.55/ 23.47 GFLOPS | Progress: (8/20) | 10.09 s
[Task 23/25] Current/Best: 3.08/ 23.47 GFLOPS | Progress: (12/20) | 13.29 s
[Task 23/25] Current/Best: 10.32/ 23.47 GFLOPS | Progress: (16/20) | 16.68 s
[Task 23/25] Current/Best: 13.60/ 23.47 GFLOPS | Progress: (20/20) | 19.45 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 4.92/ 4.92 GFLOPS | Progress: (4/20) | 13.13 s
[Task 24/25] Current/Best: 1.13/ 4.92 GFLOPS | Progress: (8/20) | 24.13 s
[Task 24/25] Current/Best: 4.74/ 4.92 GFLOPS | Progress: (12/20) | 35.10 s
[Task 24/25] Current/Best: 9.57/ 9.57 GFLOPS | Progress: (16/20) | 47.35 s
[Task 24/25] Current/Best: 3.28/ 9.57 GFLOPS | Progress: (20/20) | 58.30 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 3.21/ 8.15 GFLOPS | Progress: (4/20) | 7.68 s
[Task 25/25] Current/Best: 1.55/ 8.15 GFLOPS | Progress: (8/20) | 9.18 s Done.
Done.
-
[Task 21/25] Current/Best: 19.26/ 22.24 GFLOPS | Progress: (4/20) | 5.56 s
[Task 21/25] Current/Best: 9.36/ 22.24 GFLOPS | Progress: (8/20) | 9.05 s
[Task 21/25] Current/Best: 14.14/ 22.24 GFLOPS | Progress: (12/20) | 11.95 s
[Task 21/25] Current/Best: 14.69/ 22.24 GFLOPS | Progress: (16/20) | 13.82 s
[Task 21/25] Current/Best: 6.40/ 22.24 GFLOPS | Progress: (20/20) | 16.44 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 12.04/ 12.79 GFLOPS | Progress: (4/20) | 7.64 s
[Task 22/25] Current/Best: 3.12/ 23.40 GFLOPS | Progress: (8/20) | 10.52 s
[Task 22/25] Current/Best: 19.24/ 23.40 GFLOPS | Progress: (12/20) | 12.35 s
[Task 22/25] Current/Best: 17.41/ 23.40 GFLOPS | Progress: (16/20) | 14.34 s
[Task 22/25] Current/Best: 7.83/ 23.40 GFLOPS | Progress: (20/20) | 16.30 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 5.44/ 22.49 GFLOPS | Progress: (4/20) | 6.06 s
[Task 23/25] Current/Best: 6.23/ 22.49 GFLOPS | Progress: (8/20) | 9.85 s
[Task 23/25] Current/Best: 19.36/ 22.49 GFLOPS | Progress: (12/20) | 13.65 s
[Task 23/25] Current/Best: 5.44/ 22.49 GFLOPS | Progress: (16/20) | 16.34 s
[Task 23/25] Current/Best: 2.71/ 22.49 GFLOPS | Progress: (20/20) | 20.60 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 10.22/ 10.22 GFLOPS | Progress: (4/20) | 13.78 s
[Task 24/25] Current/Best: 9.24/ 10.22 GFLOPS | Progress: (8/20) | 26.12 s
[Task 24/25] Current/Best: 0.61/ 10.22 GFLOPS | Progress: (12/20) | 30.32 s
[Task 24/25] Current/Best: 8.09/ 10.22 GFLOPS | Progress: (16/20) | 40.68 s
[Task 24/25] Current/Best: 1.22/ 10.22 GFLOPS | Progress: (20/20) | 53.36 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 25/25] Current/Best: 1.55/ 6.03 GFLOPS | Progress: (4/20) | 5.99 s
[Task 25/25] Current/Best: 5.96/ 6.03 GFLOPS | Progress: (8/20) | 16.96 s
[Task 25/25] Current/Best: 5.95/ 8.17 GFLOPS | Progress: (12/20) | 27.93 s
[Task 25/25] Current/Best: 8.33/ 8.33 GFLOPS | Progress: (16/20) | 31.88 s
[Task 25/25] Current/Best: 2.77/ 8.33 GFLOPS | Progress: (20/20) | 37.50 s
+
[Task 25/25] Current/Best: 1.55/ 8.27 GFLOPS | Progress: (12/20) | 11.03 s
[Task 25/25] Current/Best: 3.23/ 8.27 GFLOPS | Progress: (16/20) | 22.03 s
[Task 25/25] Current/Best: 3.50/ 8.27 GFLOPS | Progress: (20/20) | 34.42 s
@@ -665,7 +665,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123045 tabby, tabby cat' with probability=0.621102
class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -723,8 +723,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 405.78551404999644, 'median': 405.6996923999918, 'std': 0.9185659256848557}
- unoptimized: {'mean': 485.39099493000094, 'median': 485.2391821500021, 'std': 1.1640439743505182}
+ optimized: {'mean': 408.6111357099958, 'median': 409.75637514999335, 'std': 4.784204697403965}
+ unoptimized: {'mean': 508.9282783900012, 'median': 509.54074805000573, 'std': 1.5907018118433454}
@@ -747,7 +747,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 11 minutes 59.755 seconds)
+ **Total running time of the script:** ( 12 minutes 20.379 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 9315243713..1544153b68 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -274,7 +274,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.336e-07 secs/op
+ 1.342e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 4866470649..4c01d6bc38 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -270,7 +270,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x231293b0)), stage(b, placeholder(b, 0x2a176010)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T [...]
+ [stage(a, placeholder(a, 0x9817330)), stage(b, placeholder(b, 0x113acf10)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[a[ax0, ax1, ax2] * b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T. [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 5ebe4f59b2..a2c5880e37 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**15:31.903** total execution time for **tutorial** files:
+**16:15.802** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:59.755 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:20.379 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:27.679 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:36.897 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.899 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.267 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:37.283 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:36.942 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.889 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.624 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.362 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.656 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.860 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.871 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.175 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.166 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 010a306609..ca078f9687 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -389,7 +389,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000008
@@ -444,7 +444,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000026
+ vector: 0.000034
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.77233000007982e-06 1.0
- naive 6.696499999999999e-06 0.8615820481028506
- parallel 6.9913e-06 0.8995114720975822
- vector 2.6369700000000003e-05 3.3927663904812575
+ numpy 8.086299999376934e-06 1.0
+ naive 6.9577e-06 0.8604306049164767
+ parallel 7.5797000000000005e-06 0.9373508280157837
+ vector 3.38113e-05 4.181306654787138
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018751
+ Numpy running time: 0.018736
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.382162
+ none: 3.506791
@@ -1080,7 +1080,7 @@ schedule.
.. code-block:: none
- blocking: 0.314402
+ blocking: 0.301348
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.344549
+ vectorization: 0.336904
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1230,7 +1230,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116712
+ loop permutation: 0.114751
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1321,7 +1321,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.107431
+ array packing: 0.108123
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1404,7 +1404,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111194
+ block caching: 0.111043
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1478,7 +1478,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146423
+ parallelization: 0.146087
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1548,13 +1548,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.382161504 1.0
- blocking 0.3144017308 0.09295881655212643
- vectorization 0.34454892519999997 0.10187240461240847
- loop permutation 0.11671236069999999 0.034508216287710426
- array packing 0.10743148389999999 0.031764149575040514
- block caching 0.1111941343 0.03287664831158814
- parallelization 0.146422571 0.04329260173614702
+ none 3.5067909512 1.0
+ blocking 0.3013484693 0.08593282961360459
+ vectorization 0.3369037844 0.09607181867647795
+ loop permutation 0.1147505066 0.03272236874021052
+ array packing 0.1081231563 0.030832506928592643
+ block caching 0.111042525 0.03166499701443623
+ parallelization 0.1460868507 0.04165827183111958
@@ -1596,7 +1596,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.899 seconds)
+ **Total running time of the script:** ( 1 minutes 2.267 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 4798308e1e..156f4dea50 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-a7a1980480b865669f18962ae7f1518321450be4
+f79e4ebf30ebaac2fc61f690629efff6b7f8a890
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 3dd1278653..2a010451fc 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -590,7 +590,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.885 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.215 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 51ab405332..2b1a53c9aa 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -444,7 +444,7 @@
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1f3ea56b-9275-4776-8673-d5915cd2a69d 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.zip606b9c7c-de5f-48a2-900e-35609aefaa43 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 1f42ae7781..35589b8469 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -454,14 +454,14 @@ 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, 59.3MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 41.5MB/s]
- 45%|####4 | 18.5M/41.5M [00:00<00:00, 41.9MB/s]
- 55%|#####4 | 22.6M/41.5M [00:00<00:00, 32.6MB/s]
- 63%|######2 | 26.0M/41.5M [00:00<00:00, 24.5MB/s]
- 77%|#######7 | 32.0M/41.5M [00:01<00:00, 27.0MB/s]
- 96%|#########6| 40.0M/41.5M [00:01<00:00, 37.6MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 36.3MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 41.6MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 37.3MB/s]
+ 43%|####3 | 17.9M/41.5M [00:00<00:00, 34.8MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 35.4MB/s]
+ 62%|######1 | 25.7M/41.5M [00:00<00:00, 32.5MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.3MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 45.5MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 39.6MB/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 6c1a17b4a4..c595f4b761 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -437,13 +437,11 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 55.7MB/s]
- 30%|##9 | 13.3M/44.7M [00:00<00:00, 45.8MB/s]
- 40%|###9 | 17.7M/44.7M [00:00<00:00, 37.3MB/s]
- 54%|#####3 | 24.1M/44.7M [00:00<00:00, 46.3MB/s]
- 78%|#######8 | 34.9M/44.7M [00:00<00:00, 66.1MB/s]
- 94%|#########3| 41.8M/44.7M [00:00<00:00, 67.9MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 54.5MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 59.6MB/s]
+ 40%|#### | 18.1M/44.7M [00:00<00:00, 80.4MB/s]
+ 61%|######1 | 27.5M/44.7M [00:00<00:00, 87.9MB/s]
+ 90%|########9 | 40.0M/44.7M [00:00<00:00, 93.2MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 88.8MB/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 0632517fbc..54e12c8b8d 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -657,7 +657,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 32.798 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.065 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 a23d57dc7c..ffdc8fbab1 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:53.125</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:48.847</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:32.798</p></td>
+<td><p>01:30.065</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:22.885</p></td>
+<td><p>01:21.215</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>00:55.295</p></td>
+<td><p>00:56.595</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>00:37.852</p></td>
+<td><p>00:38.016</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:32.663</p></td>
+<td><p>00:31.665</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:30.788</p></td>
+<td><p>00:30.242</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>00:28.828</p></td>
+<td><p>00:28.087</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:26.366</p></td>
+<td><p>00:25.858</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>00:22.884</p></td>
+<td><p>00:24.366</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>00:02.767</p></td>
+<td><p>00:02.739</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 420bc69054..0bb75d8e1d 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -799,7 +799,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2636.3413 2635.8546 2640.6695 2634.9949 1.5893
+ 2679.8810 2679.4614 2683.8909 2678.6685 1.4501
</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_adreno_tvmc.html b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
index 1a627c590a..76d7239190 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
@@ -443,25 +443,28 @@ to run this tutorial with a real device over rpc.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
8192/102967424 [..............................] - ETA: 0s
- 9666560/102967424 [=>............................] - ETA: 0s
- 16769024/102967424 [===>..........................] - ETA: 0s
- 25157632/102967424 [======>.......................] - ETA: 0s
- 33546240/102967424 [========>.....................] - ETA: 0s
- 39223296/102967424 [==========>...................] - ETA: 0s
+ 8380416/102967424 [=>............................] - ETA: 1s
+ 16769024/102967424 [===>..........................] - ETA: 1s
+ 23412736/102967424 [=====>........................] - ETA: 0s
+ 25157632/102967424 [======>.......................] - ETA: 1s
+ 33546240/102967424 [========>.....................] - ETA: 1s
+ 40189952/102967424 [==========>...................] - ETA: 0s
41934848/102967424 [===========>..................] - ETA: 0s
48578560/102967424 [=============>................] - ETA: 0s
- 52518912/102967424 [==============>...............] - ETA: 0s
- 63627264/102967424 [=================>............] - ETA: 0s
- 68599808/102967424 [==================>...........] - ETA: 0s
- 73605120/102967424 [====================>.........] - ETA: 0s
- 77971456/102967424 [=====================>........] - ETA: 0s
- 83623936/102967424 [=======================>......] - ETA: 0s
- 88645632/102967424 [========================>.....] - ETA: 0s
- 93618176/102967424 [==========================>...] - ETA: 0s
- 94461952/102967424 [==========================>...] - ETA: 0s
+ 50323456/102967424 [=============>................] - ETA: 0s
+ 58712064/102967424 [================>.............] - ETA: 0s
+ 65355776/102967424 [==================>...........] - ETA: 0s
+ 67100672/102967424 [==================>...........] - ETA: 0s
+ 69296128/102967424 [===================>..........] - ETA: 0s
+ 71540736/102967424 [===================>..........] - ETA: 0s
+ 75489280/102967424 [====================>.........] - ETA: 0s
+ 82124800/102967424 [======================>.......] - ETA: 0s
+ 83877888/102967424 [=======================>......] - ETA: 0s
+ 90521600/102967424 [=========================>....] - ETA: 0s
+ 92266496/102967424 [=========================>....] - ETA: 0s
+ 98910208/102967424 [===========================>..] - ETA: 0s
100646912/102967424 [============================>.] - ETA: 0s
-102850560/102967424 [============================>.] - ETA: 0s
-102967424/102967424 [==============================] - 1s 0us/step
+102967424/102967424 [==============================] - 2s 0us/step
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 8639fe471c..306810f2d5 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -667,7 +667,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 14.7598 14.6373 15.7451 14.4975 0.3477
+ 15.6998 15.6305 16.1354 15.5438 0.1791
</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 20ce7cd1fc..445171477b 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -459,36 +459,33 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 4%|3 | 6.30M/170M [00:00<00:02, 60.0MB/s]
- 7%|7 | 12.0M/170M [00:00<00:03, 54.0MB/s]
- 10%|# | 17.2M/170M [00:00<00:05, 27.6MB/s]
- 13%|#3 | 22.3M/170M [00:00<00:05, 25.8MB/s]
- 15%|#4 | 25.3M/170M [00:00<00:06, 24.1MB/s]
- 19%|#8 | 32.0M/170M [00:01<00:05, 25.5MB/s]
- 24%|##3 | 40.0M/170M [00:01<00:03, 34.1MB/s]
- 28%|##8 | 48.0M/170M [00:01<00:03, 39.3MB/s]
- 33%|###3 | 56.5M/170M [00:01<00:02, 49.3MB/s]
- 37%|###6 | 62.3M/170M [00:01<00:02, 47.0MB/s]
- 40%|###9 | 67.3M/170M [00:01<00:02, 47.9MB/s]
- 43%|####2 | 72.3M/170M [00:01<00:02, 46.9MB/s]
- 47%|####7 | 80.0M/170M [00:02<00:02, 44.0MB/s]
- 51%|##### | 86.3M/170M [00:02<00:01, 48.5MB/s]
- 54%|#####3 | 91.3M/170M [00:02<00:01, 44.8MB/s]
- 57%|#####6 | 96.0M/170M [00:02<00:01, 41.3MB/s]
- 59%|#####8 | 100M/170M [00:02<00:01, 40.6MB/s]
- 61%|######1 | 104M/170M [00:02<00:02, 29.0MB/s]
- 66%|######5 | 112M/170M [00:03<00:01, 35.2MB/s]
- 71%|####### | 120M/170M [00:03<00:01, 39.0MB/s]
- 74%|#######4 | 126M/170M [00:03<00:01, 41.1MB/s]
- 77%|#######6 | 130M/170M [00:03<00:01, 37.0MB/s]
- 79%|#######9 | 134M/170M [00:03<00:01, 36.3MB/s]
- 81%|########1 | 138M/170M [00:03<00:00, 33.7MB/s]
- 85%|########4 | 144M/170M [00:03<00:00, 39.6MB/s]
- 89%|########9 | 152M/170M [00:04<00:00, 40.4MB/s]
- 93%|#########3| 158M/170M [00:04<00:00, 41.1MB/s]
- 96%|#########5| 162M/170M [00:04<00:00, 34.5MB/s]
- 99%|#########8| 168M/170M [00:04<00:00, 38.6MB/s]
-100%|##########| 170M/170M [00:04<00:00, 38.6MB/s]
+ 3%|3 | 5.18M/170M [00:00<00:03, 51.3MB/s]
+ 6%|5 | 10.1M/170M [00:00<00:04, 39.4MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:03, 44.0MB/s]
+ 13%|#3 | 22.3M/170M [00:00<00:03, 44.7MB/s]
+ 16%|#5 | 26.6M/170M [00:00<00:03, 44.6MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:03, 39.1MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:03, 45.0MB/s]
+ 28%|##8 | 48.0M/170M [00:01<00:02, 49.1MB/s]
+ 34%|###4 | 58.3M/170M [00:01<00:01, 63.2MB/s]
+ 38%|###8 | 64.8M/170M [00:01<00:01, 60.2MB/s]
+ 42%|####2 | 72.0M/170M [00:01<00:01, 63.0MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 57.7MB/s]
+ 52%|#####1 | 88.0M/170M [00:01<00:01, 53.7MB/s]
+ 56%|#####5 | 94.3M/170M [00:01<00:01, 53.1MB/s]
+ 59%|#####8 | 99.5M/170M [00:02<00:01, 51.3MB/s]
+ 62%|######1 | 105M/170M [00:02<00:01, 39.6MB/s]
+ 66%|######5 | 112M/170M [00:02<00:01, 45.9MB/s]
+ 71%|####### | 120M/170M [00:02<00:01, 49.2MB/s]
+ 74%|#######4 | 126M/170M [00:02<00:00, 51.9MB/s]
+ 77%|#######7 | 132M/170M [00:02<00:00, 52.1MB/s]
+ 80%|######## | 137M/170M [00:02<00:00, 38.5MB/s]
+ 85%|########4 | 144M/170M [00:03<00:00, 45.5MB/s]
+ 89%|########9 | 152M/170M [00:03<00:00, 51.3MB/s]
+ 93%|#########2| 157M/170M [00:03<00:00, 45.7MB/s]
+ 95%|#########5| 162M/170M [00:03<00:00, 46.1MB/s]
+ 99%|#########8| 168M/170M [00:03<00:00, 44.8MB/s]
+100%|##########| 170M/170M [00:03<00:00, 48.7MB/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=& [...]
@@ -586,7 +583,7 @@ 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 30.808 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 33.022 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 1a7918ced0..44a9a32c71 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -500,8 +500,8 @@ 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]
- 66%|######5 | 8.90M/13.6M [00:00<00:00, 93.3MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 62.3MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 62.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 58.6MB/s]
</pre></div>
</div>
</div>
@@ -592,7 +592,7 @@ 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)
- 88.0155 87.9377 92.8729 87.7785 0.5127
+ 90.3143 90.1681 98.6706 89.8865 0.8972
</pre></div>
</div>
<div class="admonition note">
@@ -631,7 +631,7 @@ 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 15.709 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.277 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 7f980647ed..0c3618ee69 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -585,7 +585,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 117.1700 117.1899 118.1862 116.4393 0.2836
+ 118.4165 118.3799 123.2114 116.1521 1.0844
</pre></div>
</div>
<div class="admonition note">
@@ -613,7 +613,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 27.391 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.227 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 8438a0f9c8..4f13298872 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -526,7 +526,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 43.421 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 48.070 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 cb234c4d54..0d886a8bc9 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -468,24 +468,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 1%|1 | 1364/132723 [00:00<00:09, 13620.56KB/s]
- 3%|3 | 4293/132723 [00:00<00:05, 22830.21KB/s]
- 7%|7 | 9328/132723 [00:00<00:03, 35128.75KB/s]
- 12%|#1 | 15863/132723 [00:00<00:02, 47001.88KB/s]
- 18%|#8 | 24515/132723 [00:00<00:01, 61207.79KB/s]
- 25%|##5 | 33200/132723 [00:00<00:01, 69899.40KB/s]
- 32%|###1 | 41904/132723 [00:00<00:01, 75493.12KB/s]
- 38%|###8 | 50569/132723 [00:00<00:01, 79040.31KB/s]
- 45%|####4 | 59306/132723 [00:00<00:00, 81641.28KB/s]
- 51%|#####1 | 68064/132723 [00:01<00:00, 83472.08KB/s]
- 58%|#####7 | 76830/132723 [00:01<00:00, 84749.90KB/s]
- 64%|######4 | 85307/132723 [00:01<00:00, 76070.74KB/s]
- 71%|####### | 94037/132723 [00:01<00:00, 79217.33KB/s]
- 77%|#######7 | 102800/132723 [00:01<00:00, 81622.85KB/s]
- 84%|########4 | 111559/132723 [00:01<00:00, 83352.52KB/s]
- 90%|######### | 119979/132723 [00:01<00:00, 78052.80KB/s]
- 97%|#########7| 128760/132723 [00:01<00:00, 80792.80KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 68842.75KB/s]
+ 1%| | 1304/132723 [00:00<00:10, 13006.34KB/s]
+ 3%|3 | 4088/132723 [00:00<00:05, 21657.15KB/s]
+ 7%|7 | 9793/132723 [00:00<00:03, 37780.29KB/s]
+ 14%|#3 | 18341/132723 [00:00<00:02, 56583.47KB/s]
+ 20%|## | 26924/132723 [00:00<00:01, 67117.91KB/s]
+ 27%|##6 | 35418/132723 [00:00<00:01, 73170.84KB/s]
+ 33%|###3 | 44025/132723 [00:00<00:01, 77377.58KB/s]
+ 40%|###9 | 52634/132723 [00:00<00:00, 80148.72KB/s]
+ 46%|####6 | 61265/132723 [00:00<00:00, 82070.78KB/s]
+ 53%|#####2 | 69897/132723 [00:01<00:00, 83379.03KB/s]
+ 59%|#####9 | 78466/132723 [00:01<00:00, 84084.85KB/s]
+ 66%|######5 | 87065/132723 [00:01<00:00, 84662.28KB/s]
+ 72%|#######2 | 95723/132723 [00:01<00:00, 85238.81KB/s]
+ 79%|#######8 | 104248/132723 [00:01<00:00, 70780.99KB/s]
+ 85%|########4 | 112197/132723 [00:01<00:00, 73075.63KB/s]
+ 90%|######### | 119822/132723 [00:01<00:00, 52353.27KB/s]
+ 97%|#########6| 128449/132723 [00:01<00:00, 59703.95KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 67378.08KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -524,7 +524,7 @@ 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 59.187 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 55.455 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 92312bbcfa..eb24d5c9c9 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>16:20.756</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>16:27.773</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:59.187</p></td>
+<td><p>03:55.455</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:30.808</p></td>
+<td><p>03:33.022</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>02:27.391</p></td>
+<td><p>02:28.227</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>01:43.421</p></td>
+<td><p>01:48.070</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>01:15.709</p></td>
+<td><p>01:16.277</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>00:55.776</p></td>
+<td><p>00:56.392</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_adreno_tvmc.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-tvmc-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno™ with tvmc Interface</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno_tvmc.py</span></code>)</p></td>
-<td><p>00:50.440</p></td>
+<td><p>00:51.909</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:42.477</p></td>
+<td><p>00:42.620</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:28.095</p></td>
+<td><p>00:28.102</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:27.447</p></td>
+<td><p>00:27.692</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 3db2f730d0..8ff8594c43 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -624,7 +624,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipaf5dd4c9-a675-4fbc-9418-72a52f0eea71 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.zipc93d54ad-2f79-452a-85a7-10ed78b12878 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 89662fd61f..5705ea2f42 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:55.415</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:53.883</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:51.557</p></td>
+<td><p>00:50.143</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>00:02.768</p></td>
+<td><p>00:02.684</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>00:01.083</p></td>
+<td><p>00:01.049</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index dc115c3290..a111cecd9b 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -531,10 +531,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 22201us [22201us] (48.61%; 48.61%)
-FoldScaleAxis: 23474us [7us] (51.39%; 51.39%)
- FoldConstant: 23467us [1736us] (51.38%; 99.97%)
- InferType: 21731us [21731us] (47.58%; 92.60%)
+InferType: 22194us [22194us] (48.80%; 48.80%)
+FoldScaleAxis: 23286us [7us] (51.20%; 51.20%)
+ FoldConstant: 23279us [1675us] (51.18%; 99.97%)
+ InferType: 21604us [21604us] (47.50%; 92.80%)
</pre></div>
</div>
</div>
@@ -556,10 +556,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 21828us [21828us] (48.21%; 48.21%)
-FoldScaleAxis: 23451us [5us] (51.79%; 51.79%)
- FoldConstant: 23446us [1693us] (51.78%; 99.98%)
- InferType: 21753us [21753us] (48.04%; 92.78%)
+InferType: 21621us [21621us] (48.34%; 48.34%)
+FoldScaleAxis: 23102us [5us] (51.66%; 51.66%)
+ FoldConstant: 23097us [1684us] (51.65%; 99.98%)
+ InferType: 21413us [21413us] (47.88%; 92.71%)
</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 84fb993666..835c707c9b 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -580,7 +580,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 53.126945 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 53.545089 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 b7b33aeceb..7c320509a0 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -862,7 +862,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.840041 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.243044 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 f05c826ee5..dc8cd42eff 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -477,8 +477,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.016620
-Baseline: 3.385342
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017691
+Baseline: 3.412250
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -537,7 +537,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296053
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.291376
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332443
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.326029
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -649,7 +649,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114155
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117350
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -726,7 +726,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.107448
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110147
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -804,7 +804,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.102262
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110723
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -884,7 +884,7 @@ class Module:
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.134265
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146654
</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 6fd66419e1..cfea5c9bd7 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.142</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.082</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.170</p></td>
+<td><p>00:32.079</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>00:01.873</p></td>
+<td><p>00:01.866</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>00:01.099</p></td>
+<td><p>00:01.137</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 d02d8700ca..3ab7dd2f4e 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:57.586</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>10:11.065</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -354,27 +354,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>06:05.927</p></td>
+<td><p>06:15.276</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>01:41.092</p></td>
+<td><p>01:41.979</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>01:10.523</p></td>
+<td><p>01:10.781</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>00:32.605</p></td>
+<td><p>00:35.466</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>00:13.975</p></td>
+<td><p>00:14.083</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:13.464</p></td>
+<td><p>00:13.480</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 81805642f3..e09123b76a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -510,64 +510,423 @@ class Module:
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- blockIdx_x = T.launch_thread("blockIdx.x", 128)
- conv2d_nchw = T.allocate([4], "float32", "local")
- pad_temp_shared = T.allocate([3136], "float32", "shared")
- kernel_shared = T.allocate([256], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 49)
- conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
+ blockIdx_x = T.launch_thread("blockIdx.x", 224)
+ conv2d_nchw = T.allocate([2], "float32", "local")
+ pad_temp_shared = T.allocate([144], "float32", "shared")
+ kernel_shared = T.allocate([768], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 56)
+ conv2d_nchw_1 = T.Buffer((2,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[3] = T.float32(0)
- for rc_outer_outer, ry_outer_outer, rx_outer_outer in T.grid(8, 3, 3):
- cse_var_2: T.int32 = rc_outer_outer * 576
- cse_var_1: T.int32 = ry_outer_outer * 3
- pad_temp_shared_1 = T.Buffer((3136,), data=pad_temp_shared, scope="shared")
- for ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer in range(64):
- cse_var_3: T.int32 = ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49
- threadIdx_x_1 = T.launch_thread("threadIdx.x", 49)
- data_1 = T.Buffer((25088,), data=data.data)
- pad_temp_shared_1[cse_var_3 + threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 // 7 + ry_outer_outer and threadIdx_x_1 // 7 + ry_outer_outer < 8 and 1 <= rx_outer_outer + threadIdx_x_1 % 7 and rx_outer_outer + threadIdx_x_1 % 7 < 8, data_1[rc_outer_outer * 3136 + cse_var_3 + ry_outer_outer * 7 + rx_outer_outer + threadIdx_x_1 - 8], T.float32(0))
+ for rc_outer_outer in range(32):
+ cse_var_2: T.int32 = rc_outer_outer * 784
+ cse_var_1: T.int32 = rc_outer_outer * 144
threadIdx_x_1 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((256,), data=kernel_shared, scope="shared")
+ pad_temp_shared_1 = T.Buffer((144,), data=pad_temp_shared, scope="shared")
+ data_1 = T.Buffer((25088,), data=data.data)
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8 and 1 <= blockIdx_x % 7, data_1[cse_var_2 + threadIdx_x_1 // 9 * 49 + threadIdx_x_1 % 9 * 7 + blockIdx_x % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8 and 1 <= blockIdx_x % 7, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 9 * 49 + (threadIdx_x_1 + 2) % 9 * 7 + blockIdx_x % 7 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ if T.likely(threadIdx_x_1 < 32):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8 and 1 <= blockIdx_x % 7, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 9 * 49 + (threadIdx_x_1 + 4) % 9 * 7 + blockIdx_x % 7 - 8], T.float32(0))
+ threadIdx_x_2 = T.env_thread("threadIdx.x")
+ kernel_shared_1 = T.Buffer((768,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x * 18432 + cse_var_2 + threadIdx_x_1 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1 + 49] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 49) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 49) % 64 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1 + 98] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 98) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 34) % 64 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1 + 147] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 147) // 64 * 4608 + cse_var_2 + (threadIdx_x_1 + 19) % 64 * 9 + cse_var_1 + rx_outer_outer]
- with T.launch_thread(threadIdx_x_1, 49):
- kernel_shared_1[threadIdx_x_1 + 196] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 196) // 64 * 4608 + cse_var_2 + threadIdx_x_1 * 9 + cse_var_1 + rx_outer_outer + 36]
- with T.launch_thread(threadIdx_x_1, 49):
- if T.likely(threadIdx_x_1 < 11):
- kernel_shared_1[threadIdx_x_1 + 245] = kernel_1[blockIdx_x * 18432 + (threadIdx_x_1 + 245) // 64 * 4608 + cse_var_2 + threadIdx_x_1 * 9 + cse_var_1 + rx_outer_outer + 477]
- for rc_outer_inner in range(16):
- cse_var_4: T.int32 = rc_outer_inner * 4
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x] * kernel_shared_1[cse_var_4]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x] * kernel_shared_1[cse_var_4 + 128]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 49] * kernel_shared_1[cse_var_4 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 49] * kernel_shared_1[cse_var_4 + 129]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 98] * kernel_shared_1[cse_var_4 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 98] * kernel_shared_1[cse_var_4 + 130]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 147] * kernel_shared_1[cse_var_4 + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 147] * kernel_shared_1[cse_var_4 + 131]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x] * kernel_shared_1[cse_var_4 + 64]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x] * kernel_shared_1[cse_var_4 + 192]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 49] * kernel_shared_1[cse_var_4 + 65]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 49] * kernel_shared_1[cse_var_4 + 193]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 98] * kernel_shared_1[cse_var_4 + 66]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 98] * kernel_shared_1[cse_var_4 + 194]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 147] * kernel_shared_1[cse_var_4 + 67]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 196 + threadIdx_x + 147] * kernel_shared_1[cse_var_4 + 195]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 56) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 56) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 112) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 112) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 168) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 168) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 224) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 224) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 280) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 280) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 32256]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 392) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 392) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 448) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 448) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 504) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 504) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 560) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 560) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 616) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 616) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 64512]
+ with T.launch_thread(threadIdx_x_2, 56):
+ if T.likely(threadIdx_x_2 < 40):
+ kernel_shared_1[(threadIdx_x_2 + 728) // 48 * 48 + (threadIdx_x_2 + 8) // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 728) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 36]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 42]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 93]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 37]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 43]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 94]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 38]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 44]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 95]
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 49 + threadIdx_x_1 % 9 * 7 + blockIdx_x % 7 - 7], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 9 * 49 + (threadIdx_x_1 + 2) % 9 * 7 + blockIdx_x % 7 - 7], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ if T.likely(threadIdx_x_1 < 32):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 9 * 49 + (threadIdx_x_1 + 4) % 9 * 7 + blockIdx_x % 7 - 7], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 56) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 56) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 112) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 112) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 168) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 168) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 224) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 224) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 280) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 280) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 32257]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 392) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 392) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 448) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 448) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 504) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 504) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 560) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 560) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 616) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 616) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 1]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 64513]
+ with T.launch_thread(threadIdx_x_2, 56):
+ if T.likely(threadIdx_x_2 < 40):
+ kernel_shared_1[(threadIdx_x_2 + 728) // 48 * 48 + (threadIdx_x_2 + 8) // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 728) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 36]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 42]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 93]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 37]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 43]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 94]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 38]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 44]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 95]
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8 and blockIdx_x % 7 < 6, data_1[cse_var_2 + threadIdx_x_1 // 9 * 49 + threadIdx_x_1 % 9 * 7 + blockIdx_x % 7 - 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8 and blockIdx_x % 7 < 6, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 9 * 49 + (threadIdx_x_1 + 2) % 9 * 7 + blockIdx_x % 7 - 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 56):
+ if T.likely(threadIdx_x_1 < 32):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8 and blockIdx_x % 7 < 6, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 9 * 49 + (threadIdx_x_1 + 4) % 9 * 7 + blockIdx_x % 7 - 6], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 56) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 56) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 112) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 112) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 168) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 168) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 224) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 224) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 280) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 280) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 32258]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 392) // 48 * 48 + (threadIdx_x_2 + 8) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 392) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 448) // 48 * 48 + (threadIdx_x_2 + 16) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 448) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 16) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 504) // 48 * 48 + (threadIdx_x_2 // 3 + 8) % 16 * 3 + threadIdx_x_2 % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 504) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 // 3 + 8) % 16 * 9 + threadIdx_x_2 % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 560) // 48 * 48 + (threadIdx_x_2 + 32) % 48 // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 560) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 32) % 48 // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[(threadIdx_x_2 + 616) // 48 * 48 + (threadIdx_x_2 + 40) % 48 // 3 * 3 + (threadIdx_x_2 + 1) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 616) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 40) % 48 // 3 * 9 + (threadIdx_x_2 + 1) % 3 * 3 + 2]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x // 7 * 73728 + threadIdx_x_2 // 48 * 4608 + cse_var_1 + threadIdx_x_2 % 48 * 3 + 64514]
+ with T.launch_thread(threadIdx_x_2, 56):
+ if T.likely(threadIdx_x_2 < 40):
+ kernel_shared_1[(threadIdx_x_2 + 728) // 48 * 48 + (threadIdx_x_2 + 8) // 3 * 3 + (threadIdx_x_2 + 2) % 3] = kernel_1[blockIdx_x // 7 * 73728 + (threadIdx_x_2 + 728) // 48 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) // 3 * 9 + (threadIdx_x_2 + 2) % 3 * 3 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 36]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 42]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 45]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 96 + 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 96 + 51]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 96 + 54]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 96 + 57]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 96 + 60]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 96 + 63]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 96 + 66]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 96 + 69]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 96 + 72]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 96 + 75]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 96 + 78]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 96 + 81]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 96 + 84]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 96 + 87]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 96 + 90]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 96 + 93]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 37]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 43]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 46]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 96 + 49]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 96 + 52]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 96 + 55]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 96 + 58]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 96 + 61]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 96 + 64]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 96 + 67]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 96 + 70]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 96 + 73]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 96 + 76]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 96 + 79]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 96 + 82]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 96 + 85]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 96 + 88]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 96 + 91]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 96 + 94]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 38]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 44]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 47]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 96 + 50]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 96 + 53]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 96 + 56]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 96 + 59]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 96 + 62]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 96 + 65]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 96 + 68]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 96 + 71]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 96 + 74]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 96 + 77]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 96 + 80]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 96 + 83]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 96 + 86]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 96 + 89]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 96 + 92]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 96 + 95]
for i1_inner in range(2):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 196 + i1_inner * 49 + threadIdx_x] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 4 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 196 + i1_inner * 49 + threadIdx_x + 98] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 4 + i1_inner + 2], T.float32(0))
+ compute_1[blockIdx_x // 7 * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + blockIdx_x % 7] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x // 7 * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -601,7 +960,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.308 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.443 ms
</pre></div>
</div>
</div>
@@ -632,20 +991,20 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
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=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=1)
-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_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=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=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_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_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=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
@@ -653,13 +1012,13 @@ 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=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
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)
@@ -679,14 +1038,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+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=56)
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=49)
+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=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -711,54 +1070,373 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[3136];
- __shared__ float kernel_shared[256];
+extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[2];
+ __shared__ float pad_temp_shared[144];
+ __shared__ float kernel_shared[768];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 64; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49) + ((int)threadIdx.x))] = (((((1 <= ((((int)threadIdx.x) / 7) + ry_outer_outer)) && (((((int)threadIdx.x) / 7) + ry_outer_outer) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 49)) + (ry_outer_outer * 7)) + rx_outer_outer) [...]
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 18432) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 49) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 49) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 98) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 34) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 147) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 19) & 63) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 196) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 36)];
- if (((int)threadIdx.x) < 11) {
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[(((((((((int)blockIdx.x) * 18432) + (((((int)threadIdx.x) + 245) >> 6) * 4608)) + (rc_outer_outer * 576)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + rx_outer_outer) + 477)];
- }
- __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 * 196) + ((int)threadIdx.x))] * kernel_shared[(rc_outer_inner * 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 196) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 4) + 128)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 49)] * kernel_shared[((rc_outer_inner * 4) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 49)] * kernel_shared[((rc_outer_inner * 4) + 129)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 98)] * kernel_shared[((rc_outer_inner * 4) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 98)] * kernel_shared[((rc_outer_inner * 4) + 130)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 147)] * kernel_shared[((rc_outer_inner * 4) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 147)] * kernel_shared[((rc_outer_inner * 4) + 131)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 196) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 4) + 64)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 196) + ((int)threadIdx.x))] * kernel_shared[((rc_outer_inner * 4) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 49)] * kernel_shared[((rc_outer_inner * 4) + 65)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 49)] * kernel_shared[((rc_outer_inner * 4) + 193)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 98)] * kernel_shared[((rc_outer_inner * 4) + 66)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 98)] * kernel_shared[((rc_outer_inner * 4) + 194)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 147)] * kernel_shared[((rc_outer_inner * 4) + 67)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 196) + ((int)threadIdx.x)) + 147)] * kernel_shared[((rc_outer_inner * 4) + 195)]));
- }
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) && (1 <= (((int)blockIdx.x) % 7))) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) && (1 <= (((int)blockIdx.x) % 7))) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 9) * 49)) + (((((int)threadIdx.x) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) && (1 <= (((int)blockIdx.x) % 7))) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 9) * 49)) + (((((int)threadIdx.x) + 4) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 56) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 112) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 168) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 224) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 280) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 32256)];
+ kernel_shared[(((((((int)threadIdx.x) + 392) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 504) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 560) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 616) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 64512)];
+ if (((int)threadIdx.x) < 40) {
+ kernel_shared[(((((((int)threadIdx.x) + 728) / 48) * 48) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3))];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 9) * 49)) + (((((int)threadIdx.x) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 9) * 49)) + (((((int)threadIdx.x) + 4) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 56) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 112) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 168) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 224) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 280) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 32257)];
+ kernel_shared[(((((((int)threadIdx.x) + 392) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 504) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 560) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ kernel_shared[(((((((int)threadIdx.x) + 616) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 64513)];
+ if (((int)threadIdx.x) < 40) {
+ kernel_shared[(((((((int)threadIdx.x) + 728) / 48) * 48) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 1)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (((int)threadIdx.x) % 9)) && ((((int)threadIdx.x) % 9) < 8)) && ((((int)blockIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 9) * 49)) + ((((int)threadIdx.x) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = ((((1 <= ((((int)threadIdx.x) + 2) % 9)) && (((((int)threadIdx.x) + 2) % 9) < 8)) && ((((int)blockIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 56) / 9) * 49)) + (((((int)threadIdx.x) + 2) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((1 <= ((((int)threadIdx.x) + 4) % 9)) && (((((int)threadIdx.x) + 4) % 9) < 8)) && ((((int)blockIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 9) * 49)) + (((((int)threadIdx.x) + 4) % 9) * 7)) + (((int)blockIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 56) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 112) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 168) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 224) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 280) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 32258)];
+ kernel_shared[(((((((int)threadIdx.x) + 392) / 48) * 48) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 392) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 8) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 48) * 48) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 448) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 16) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 504) / 48) * 48) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 3)) + (((int)threadIdx.x) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 504) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) / 3) + 8) & 15) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 560) / 48) * 48) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 560) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 32) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ kernel_shared[(((((((int)threadIdx.x) + 616) / 48) * 48) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 616) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 40) % 48) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) / 7) * 73728) + ((((int)threadIdx.x) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) % 48) * 3)) + 64514)];
+ if (((int)threadIdx.x) < 40) {
+ kernel_shared[(((((((int)threadIdx.x) + 728) / 48) * 48) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 73728) + (((((int)threadIdx.x) + 728) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + 2)];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 96) + 95)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 4) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 196) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 4) + i1_inner) + 2)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -793,7 +1471,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 5.927 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 15.276 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 74f2ed2d3b..506a6bc3f5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -921,7 +921,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.1280 8.1314 8.1316 8.1210 0.0049
+ 8.1472 8.1423 8.1573 8.1418 0.0072
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.523 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.781 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 8f5df334f7..1fbb338e78 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -940,7 +940,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 739.1851 738.1802 741.9351 737.4398 1.9679
+ 755.4219 755.5400 756.4996 754.2260 0.9319
</pre></div>
</div>
</div>
@@ -962,7 +962,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.092 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.979 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 ad2ae94797..b3ace5a0b2 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -637,10 +637,10 @@ class Module:
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.Buffer((1024,), data=compute_1)
- for i_inner_init in range(64):
+ for i0_outer_i1_outer_fused in T.parallel(256):
+ compute_1 = T.allocate([256], "float32", "global")
+ compute_2 = T.Buffer((256,), data=compute_1)
+ for i_inner_init in range(16):
cse_var_1: T.int32 = i_inner_init * 16
compute_2[cse_var_1] = T.float32(0)
compute_2[cse_var_1 + 1] = T.float32(0)
@@ -658,7 +658,7 @@ class Module:
compute_2[cse_var_1 + 13] = T.float32(0)
compute_2[cse_var_1 + 14] = T.float32(0)
compute_2[cse_var_1 + 15] = T.float32(0)
- for elem_idx, i_inner in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i0_outer_i1_outer_fused % 32}), 64):
+ for elem_idx, i_inner in T.grid(T.Let(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i0_outer_i1_outer_fused % 32}), 16):
cse_var_2 = T.int32()
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
cse_var_3: T.int32 = i0_outer_i1_outer_fused % 32
@@ -667,54 +667,54 @@ class Module:
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_4: T.int32 = i_inner * 16
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_5: T.int32 = i_inner * 16 + 1
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_6: T.int32 = i_inner * 16 + 2
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_7: T.int32 = i_inner * 16 + 3
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_8: T.int32 = i_inner * 16 + 4
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_9: T.int32 = i_inner * 16 + 5
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_10: T.int32 = i_inner * 16 + 6
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_11: T.int32 = i_inner * 16 + 7
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_12: T.int32 = i_inner * 16 + 8
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_13: T.int32 = i_inner * 16 + 9
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 9] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 9] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_14: T.int32 = i_inner * 16 + 10
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 10] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 10] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_15: T.int32 = i_inner * 16 + 11
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 11] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 11] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_16: T.int32 = i_inner * 16 + 12
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 12] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 12] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_17: T.int32 = i_inner * 16 + 13
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 13] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 13] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_18: T.int32 = i_inner * 16 + 14
- compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 14] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 14] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
if T.likely(elem_idx < placeholder_5[cse_var_3 + 1] - placeholder_5[cse_var_3]):
cse_var_19: T.int32 = i_inner * 16 + 15
- compute_2[cse_var_19] = compute_2[cse_var_19] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 15] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 16384 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
- for i0_inner in range(64):
- cse_var_20: T.int32 = i0_outer_i1_outer_fused // 32 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
+ compute_2[cse_var_19] = compute_2[cse_var_19] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + 15] * T.max(placeholder_7[i0_outer_i1_outer_fused // 32 * 4096 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner in range(16):
+ cse_var_20: T.int32 = i0_outer_i1_outer_fused // 32 * 8192 + i0_inner * 512 + i0_outer_i1_outer_fused % 32 * 16
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
compute_3[cse_var_20:cse_var_20 + 16] = T.max(compute_2[i0_inner * 16:i0_inner * 16 + 16] + placeholder_5[cse_var_20:cse_var_20 + 16], T.Broadcast(T.float32(0), 16))
@@ -751,7 +751,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.697 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.941 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 85b931da1b..a5ab4fb624 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.530</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:40.987</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:44.496</p></td>
+<td><p>00:40.953</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 8031dc0196..bebd9c63e2 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -695,7 +695,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3983708
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 128, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6143818
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -818,9 +818,8 @@ 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, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9153411
-No: 3 GFLOPS: 254.83/254.83 result: MeasureResult(costs=(0.0009084488378378379,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.209742546081543, timestamp=1681199202.8271508) [('tile_f', [-1, 1, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2146868
-No: 4 GFLOPS: 0.00/254.83 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2047328
+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
@@ -942,8 +941,9 @@ 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, 1, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,157950
-No: 5 GFLOPS: 0.00/254.83 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9870382
+No: 4 GFLOPS: 8.10/8.10 result: MeasureResult(costs=(0.02856754475,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.651654005050659, timestamp=1681204183.3537586) [('tile_f', [-1, 16, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7036804
+No: 5 GFLOPS: 0.00/8.10 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1065,9 +1065,9 @@ 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, 16, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5195763
-No: 6 GFLOPS: 6.95/254.83 result: MeasureResult(costs=(0.0333320655,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.989668369293213, timestamp=1681199210.3548458) [('tile_f', [-1, 16, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8751858
-No: 7 GFLOPS: 0.00/254.83 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3246623
+No: 6 GFLOPS: 161.97/161.97 result: MeasureResult(costs=(0.0014293008333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9774255752563477, timestamp=1681204186.9771235) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3561056
+No: 7 GFLOPS: 0.00/161.97 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
@@ -1189,11 +1189,8 @@ 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, 128, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3451630
-No: 8 GFLOPS: 25.24/254.83 result: MeasureResult(costs=(0.009173023833333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=7.264514207839966, timestamp=1681199212.786609) [('tile_f', [-1, 4, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8959952
-No: 9 GFLOPS: 6.25/254.83 result: MeasureResult(costs=(0.037047798,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.417418956756592, timestamp=1681199215.391768) [('tile_f', [-1, 16, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5240643
-No: 10 GFLOPS: 806.76/806.76 result: MeasureResult(costs=(0.00028695028520499103,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.779116153717041, timestamp=1681199216.5159807) [('tile_f', [-1, 1, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9693065
-No: 11 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9439487
+No: 8 GFLOPS: 0.00/161.97 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
@@ -1315,8 +1312,8 @@ 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, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,124811
-No: 12 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10008720
+No: 9 GFLOPS: 0.00/161.97 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
@@ -1438,8 +1435,8 @@ 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, 1, 512]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,904859
-No: 13 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3047483
+No: 10 GFLOPS: 0.00/161.97 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
@@ -1561,11 +1558,8 @@ 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, 16, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7122399
-No: 14 GFLOPS: 18.23/806.76 result: MeasureResult(costs=(0.012698629181818182,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.832524061203003, timestamp=1681199220.1907861) [('tile_f', [-1, 16, 2, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6509154
-No: 15 GFLOPS: 1.64/806.76 result: MeasureResult(costs=(0.14085453774999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.732933044433594, timestamp=1681199222.5791147) [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3915984
-No: 16 GFLOPS: 48.07/806.76 result: MeasureResult(costs=(0.004815445285714285,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2162880897521973, timestamp=1681199223.4586391) [('tile_f', [-1, 4, 2, 1]), ('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, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6393432
-No: 17 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6953672
+No: 11 GFLOPS: 0.00/161.97 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
@@ -1687,9 +1681,8 @@ 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, 4, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3031186
-No: 18 GFLOPS: 156.70/806.76 result: MeasureResult(costs=(0.001477364425925926,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9475483894348145, timestamp=1681199225.576632) [('tile_f', [-1, 2, 64, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3562995
-No: 19 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 8, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2883749
+No: 12 GFLOPS: 0.00/161.97 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
@@ -1811,8 +1804,8 @@ 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, 512, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2606614
-No: 20 GFLOPS: 0.00/806.76 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10205865
+No: 13 GFLOPS: 0.00/161.97 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
@@ -1934,7 +1927,502 @@ 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, 16, 1, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10436364
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6507423
+No: 14 GFLOPS: 0.00/161.97 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2965851
+No: 15 GFLOPS: 0.00/161.97 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8194189
+No: 16 GFLOPS: 0.00/161.97 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,700279
+No: 17 GFLOPS: 7.84/161.97 result: MeasureResult(costs=(0.029516136,), error_no=MeasureErrorNo.NO_ERROR, all_cost=6.433065414428711, timestamp=1681204194.00447) [('tile_f', [-1, 64, 4, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8555605
+No: 18 GFLOPS: 0.00/161.97 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
+ func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
+ func = build(s, args, target=target, runtime=runtime)
+ File "/workspace/python/tvm/driver/build_module.py", line 227, in build
+ input_mod = lower(inputs, args, name=name, binds=binds)
+ File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
+ return ffi.lower_schedule(inp, args, name, binds, simple_mode)
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
+ File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
+tvm._ffi.base.TVMError: Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
+
+Traceback (most recent call last):
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:101
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2959382
+No: 19 GFLOPS: 141.09/161.97 result: MeasureResult(costs=(0.0016408140204081634,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5441296100616455, timestamp=1681204195.0882215) [('tile_f', [-1, 2, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1767376
+No: 20 GFLOPS: 175.13/175.13 result: MeasureResult(costs=(0.0013218766184210525,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.734405040740967, timestamp=1681204195.9468648) [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3631496
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -1973,9 +2461,9 @@ 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, 16, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9693065
+[('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3631496
Finish loading 20 records
-Time cost of this operator: 0.000574
+Time cost of this operator: 0.001668
</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 a739f8347f..29cda3f9f6 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -649,10 +649,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.7 98.725 (1, 2, 10, 10, 3) 2 1 [315.7]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.096 0.968 (1, 6, 10, 10) 1 1 [3.096]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.982 0.307 (1, 1, 10, 10, 3) 1 1 [0.982]
-Total_time - 319.779 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.9 98.745 (1, 2, 10, 10, 3) 2 1 [315.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.063 0.957 (1, 6, 10, 10) 1 1 [3.063]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.952 0.297 (1, 1, 10, 10, 3) 1 1 [0.952]
+Total_time - 319.914 - - - - -
</pre></div>
</div>
</div>
@@ -704,13 +704,13 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.3 97.346 (1, 6, 10, 10, 1) 2 1 [100.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.762 1.71 (1, 6, 10, 10) 1 1 [1.762]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.973 0.944 (1, 1, 10, 10, 3) 1 1 [0.973]
-Total_time - 103.035 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.4 97.328 (1, 6, 10, 10, 1) 2 1 [100.4]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.788 1.733 (1, 6, 10, 10) 1 1 [1.788]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.968 0.938 (1, 1, 10, 10, 3) 1 1 [0.968]
+Total_time - 103.156 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 25.374 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.622 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/9ccca8fd489a1486ac71b55a55c320c5/micro_autotune.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_autotune.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index db4f8ea460..53eb8a5997 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -460,8 +460,7 @@ 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]
- 66%|######6 | 2.27M/3.42M [00:00<00:00, 23.8MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 34.2MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 214MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -587,7 +586,7 @@ 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 17.055 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.488 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/12b9ecc04c41abaa12022061771821d1/micro_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index a60a3e9f45..fb4cd28d70 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -528,7 +528,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpom9tipxn/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp9ri8kf_i/images/random'
</pre></div>
</div>
</div>
@@ -588,8 +588,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [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/tmpom9tipxn/images/target contains 8144 images
-/tmp/tmpom9tipxn/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp9ri8kf_i/images/target contains 8144 images
+/tmp/tmp9ri8kf_i/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -701,13 +701,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 41s - loss: 0.2213 - accuracy: 0.9217 - val_loss: 0.1229 - val_accuracy: 0.9558 - 41s/epoch - 126ms/step
+328/328 - 42s - loss: 0.2122 - accuracy: 0.9251 - val_loss: 0.1189 - val_accuracy: 0.9581 - 42s/epoch - 127ms/step
Epoch 2/3
-328/328 - 35s - loss: 0.1059 - accuracy: 0.9599 - val_loss: 0.1022 - val_accuracy: 0.9600 - 35s/epoch - 106ms/step
+328/328 - 35s - loss: 0.0902 - accuracy: 0.9659 - val_loss: 0.1105 - val_accuracy: 0.9679 - 35s/epoch - 106ms/step
Epoch 3/3
-328/328 - 35s - loss: 0.0564 - accuracy: 0.9798 - val_loss: 0.1119 - val_accuracy: 0.9611 - 35s/epoch - 105ms/step
+328/328 - 34s - loss: 0.0678 - accuracy: 0.9746 - val_loss: 0.1039 - val_accuracy: 0.9694 - 34s/epoch - 105ms/step
-<keras.callbacks.History object at 0x7f6219312c50>
+<keras.callbacks.History object at 0x7f7e4d3b4810>
</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 21.025 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 32.350 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 7631b9af60..6a5821f7df 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:29.102</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:37.937</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,27 +354,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">5. Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:21.025</p></td>
+<td><p>04:32.350</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:25.374</p></td>
+<td><p>01:22.622</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:17.055</p></td>
+<td><p>01:17.488</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">3. microTVM Ahead-of-Time (AOT) Compilation</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:10.256</p></td>
+<td><p>00:10.199</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_custom_ide.html#sphx-glr-how-to-work-with-microtvm-micro-custom-ide-py"><span class="std std-ref">9. Bring microTVM to your own development environment</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_custom_ide.py</span></code>)</p></td>
-<td><p>00:08.043</p></td>
+<td><p>00:07.774</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:07.350</p></td>
+<td><p>00:07.504</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">7. Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index a119cc7891..4e4d51302c 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:36.265</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:36.373</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:31.765</p></td>
+<td><p>00:31.901</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:02.853</p></td>
+<td><p>00:02.851</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>00:01.641</p></td>
+<td><p>00:01.614</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 0e25b0ffba..88d94e16a5 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -554,7 +554,7 @@ 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 0x7f5e6246d3b0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f7be3a87200>
</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 73a70da3bd..33e1777034 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:08.760</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:08.908</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:06.077</p></td>
+<td><p>00:06.161</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>00:01.190</p></td>
+<td><p>00:01.252</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>00:00.619</p></td>
+<td><p>00:00.616</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>
@@ -370,11 +370,11 @@
<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>00:00.127</p></td>
+<td><p>00:00.130</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.062</p></td>
+<td><p>00:00.063</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
@@ -382,7 +382,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.030</p></td>
+<td><p>00:00.029</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 2412542d0d..60011897a9 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -234,7 +234,17 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/doxygen/detail_2extern_8h_source.html b/docs/reference/api/doxygen/detail_2extern_8h_source.html
index 27bb9a2a71..a24179668b 100644
--- a/docs/reference/api/doxygen/detail_2extern_8h_source.html
+++ b/docs/reference/api/doxygen/detail_2extern_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">extern.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="detail_2extern_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or m [...]
+<a href="detail_2extern_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or m [...]
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
<div class="ttc" id="namespacetvm_1_1te_html"><div class="ttname"><a href="namespacetvm_1_1te.html">tvm::te</a></div><div class="ttdoc">Tensor expression language DSL. </div><div class="ttdef"><b>Definition:</b> extracted_task.h:33</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Call_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Call.html">tvm::tir::Call</a></div><div class="ttdoc">Managed reference to CallNode. </div><div class="ttdef"><b>Definition:</b> expr.h:913</div></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 191f36a6f4..ac5ba57dbb 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1622,7 +1622,7 @@ 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>
@@ -1906,7 +1906,7 @@ 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 22435c6401..c6157ee4e1 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/a7a198048/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 4039cc5467..0dce11a541 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/a7a198048/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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 4c19617c02..62339de40d 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/a7a198048/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L357">runtime.ts:357</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L376">runtime.ts:376</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L367">runtime.ts:367</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 1e1fd6cb97..41cc6004f3 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/a7a198048/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L299">runtime.ts:299</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L320">runtime.ts:320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L327">runtime.ts:327</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index ba7febb192..da1036dd43 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/a7a198048/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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 9f7050d413..ea326c873f 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/a7a198048/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L50">runtime.ts:50</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L48">runtime.ts:48</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L77">runtime.ts:77</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L67">runtime.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L85">runtime.ts:85</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L96">runtime.ts:96</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L73">runtime.ts:73</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index ca43a9a101..730cf70f67 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -161,7 +161,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L844">runtime.ts:844</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L834">runtime.ts:834</a></li>
</ul>
</aside>
</section>
@@ -234,7 +234,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L833">runtime.ts:833</a></li>
</ul>
</aside>
</section>
@@ -251,7 +251,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L973">runtime.ts:973</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -296,7 +296,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -318,7 +318,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L901">runtime.ts:901</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -381,7 +381,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -412,7 +412,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -453,7 +453,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -491,7 +491,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L922">runtime.ts:922</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -508,7 +508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -552,7 +552,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L943">runtime.ts:943</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -577,7 +577,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -609,7 +609,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -640,7 +640,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -672,7 +672,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -695,7 +695,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -729,7 +729,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L986">runtime.ts:986</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -769,7 +769,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -817,7 +817,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -857,7 +857,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -900,7 +900,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -938,7 +938,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1014,7 +1014,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1046,7 +1046,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1078,7 +1078,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1110,7 +1110,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1141,7 +1141,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L957">runtime.ts:957</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 06134686df..0d9cf9a9ce 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/a7a198048/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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 d5c5c5dab6..42f9284aea 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L614">runtime.ts:614</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L626">runtime.ts:626</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -186,7 +186,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L653">runtime.ts:653</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L641">runtime.ts:641</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L687">runtime.ts:687</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 56104b6476..56ce980896 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/a7a198048/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L401">runtime.ts:401</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L394">runtime.ts:394</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L390">runtime.ts:390</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L388">runtime.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L392">runtime.ts:392</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -225,7 +225,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L480">runtime.ts:480</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -258,7 +258,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L524">runtime.ts:524</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -290,7 +290,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L465">runtime.ts:465</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -307,7 +307,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L458">runtime.ts:458</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -339,7 +339,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L584">runtime.ts:584</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -363,7 +363,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L553">runtime.ts:553</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index baf0be89aa..51624e633a 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -117,7 +117,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L255">runtime.ts:255</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -163,7 +163,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L264">runtime.ts:264</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 9b81f95d78..e41eb703c9 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/a7a198048/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/runtimecontext.html b/docs/reference/api/typedoc/classes/runtimecontext.html
index 16ddefdb77..b227812e29 100644
--- a/docs/reference/api/typedoc/classes/runtimecontext.html
+++ b/docs/reference/api/typedoc/classes/runtimecontext.html
@@ -132,7 +132,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L148">runtime.ts:148</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Item<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
</section>
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Size<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L144">runtime.ts:144</a></li>
</ul>
</aside>
</section>
@@ -192,7 +192,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Make<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
</section>
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Sys<wbr>Lib<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L146">runtime.ts:146</a></li>
</ul>
</aside>
</section>
@@ -219,7 +219,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -263,7 +263,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L163">runtime.ts:163</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -280,7 +280,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L208">runtime.ts:208</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
@@ -309,7 +309,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -326,7 +326,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L167">runtime.ts:167</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -343,7 +343,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index e0a885cd65..ed74ccad25 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/a7a198048/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L233">runtime.ts:233</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmarray.html b/docs/reference/api/typedoc/classes/tvmarray.html
index e273c2a238..a7fd912514 100644
--- a/docs/reference/api/typedoc/classes/tvmarray.html
+++ b/docs/reference/api/typedoc/classes/tvmarray.html
@@ -133,7 +133,7 @@
<aside class="tsd-sources">
<p>Overrides <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#constructor">constructor</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L784">runtime.ts:784</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -162,7 +162,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#ctx">ctx</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#dispose">dispose</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -197,7 +197,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L804">runtime.ts:804</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -230,7 +230,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#gethandle">getHandle</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L796">runtime.ts:796</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -283,7 +283,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typeindex">typeIndex</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -306,7 +306,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typekey">typeKey</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmobject.html b/docs/reference/api/typedoc/classes/tvmobject.html
index 80e11d4a12..8f6f27e2ce 100644
--- a/docs/reference/api/typedoc/classes/tvmobject.html
+++ b/docs/reference/api/typedoc/classes/tvmobject.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">ctx<span class="tsd-signature-symbol">:</span> <a href="runtimecontext.html" class="tsd-signature-type">RuntimeContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -175,7 +175,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -192,7 +192,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -246,7 +246,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 796455ea6d..330090b3c0 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/a7a198048/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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 3ac2ad6250..71917dbdd6 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/a7a198048/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 914ae62da1..f3104bfb96 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/a7a198048/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L812">runtime.ts:812</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L811">runtime.ts:811</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 2fd22c5b4a..1408313f28 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/a7a198048/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L339">runtime.ts:339</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L337">runtime.ts:337</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L340">runtime.ts:340</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L338">runtime.ts:338</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index cd923756ba..52d3a0c231 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/a7a198048/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 1a9de6fed8..f1c6ec5233 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/a7a198048/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 84ff8e83bc..feb654ef9f 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">FObject<wbr>Constructor<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, lib<span class="tsd-signature-symbol">: </span><a href="classes/ffilibrary.html" class="tsd-signature-type">FFILibrary</a>, ctx<span class="tsd-signature-symbol">: </span><a href="classes/runtimecontext.html" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L778">runtime.ts:778</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -288,7 +288,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -376,7 +376,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -420,7 +420,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -456,7 +456,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -508,7 +508,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -556,7 +556,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -595,7 +595,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -651,7 +651,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -687,7 +687,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -726,7 +726,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -765,7 +765,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -808,7 +808,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -838,7 +838,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -874,7 +874,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -922,7 +922,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -962,7 +962,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -998,7 +998,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Get<wbr>Type<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>obj<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1037,7 +1037,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Index2<wbr>Key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_index<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, out_type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1076,7 +1076,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMObject<wbr>Type<wbr>Key2<wbr>Index<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>type_key<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out_tindex<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1115,7 +1115,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1157,7 +1157,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1193,7 +1193,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1229,7 +1229,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1269,7 +1269,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1321,7 +1321,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1357,7 +1357,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1372,7 +1372,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L37">runtime.ts:37</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L37">runtime.ts:37</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1387,7 +1387,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1402,7 +1402,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1417,7 +1417,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Base<span class="tsd-signature-symbol">:</span> <a href="classes/tvmobject.html" class="tsd-signature-type">TVMObject</a><span class="tsd-signature-symbol"> | </span><a href="classes/ndarray.html" class="tsd-signature-type">NDArray</a><span class="tsd-signature-symbol"> | </span><a href="classes/module.html" class="tsd-signature-type">Module</a><span class="tsd-signature-symbol"> | </span><a href="index.html#packedfunc" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L781">runtime.ts:781</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L781">runtime.ts:781</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1435,7 +1435,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1457,7 +1457,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1489,7 +1489,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1518,7 +1518,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1555,7 +1555,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1586,7 +1586,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1608,7 +1608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1639,7 +1639,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1661,7 +1661,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1726,7 +1726,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1748,7 +1748,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L343">runtime.ts:343</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L343">runtime.ts:343</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1757,7 +1757,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L344">runtime.ts:344</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L344">runtime.ts:344</a></li>
</ul>
</aside>
</section>
@@ -1767,7 +1767,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L345">runtime.ts:345</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L345">runtime.ts:345</a></li>
</ul>
</aside>
</section>
@@ -1777,7 +1777,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L346">runtime.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L346">runtime.ts:346</a></li>
</ul>
</aside>
</section>
@@ -1787,7 +1787,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L347">runtime.ts:347</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L347">runtime.ts:347</a></li>
</ul>
</aside>
</section>
@@ -1798,7 +1798,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L272">runtime.ts:272</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L272">runtime.ts:272</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1807,7 +1807,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L273">runtime.ts:273</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L273">runtime.ts:273</a></li>
</ul>
</aside>
</section>
@@ -1817,7 +1817,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L277">runtime.ts:277</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L277">runtime.ts:277</a></li>
</ul>
</aside>
</section>
@@ -1827,7 +1827,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L274">runtime.ts:274</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L274">runtime.ts:274</a></li>
</ul>
</aside>
</section>
@@ -1837,7 +1837,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L275">runtime.ts:275</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L275">runtime.ts:275</a></li>
</ul>
</aside>
</section>
@@ -1847,7 +1847,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L276">runtime.ts:276</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L276">runtime.ts:276</a></li>
</ul>
</aside>
</section>
@@ -1858,7 +1858,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L280">runtime.ts:280</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L280">runtime.ts:280</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1867,7 +1867,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L283">runtime.ts:283</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L283">runtime.ts:283</a></li>
</ul>
</aside>
</section>
@@ -1877,7 +1877,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L281">runtime.ts:281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L281">runtime.ts:281</a></li>
</ul>
</aside>
</section>
@@ -1887,7 +1887,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L282">runtime.ts:282</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L282">runtime.ts:282</a></li>
</ul>
</aside>
</section>
@@ -1897,7 +1897,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L286">runtime.ts:286</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L286">runtime.ts:286</a></li>
</ul>
</aside>
</section>
@@ -1907,7 +1907,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L284">runtime.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L284">runtime.ts:284</a></li>
</ul>
</aside>
</section>
@@ -1917,7 +1917,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L285">runtime.ts:285</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L285">runtime.ts:285</a></li>
</ul>
</aside>
</section>
@@ -1927,7 +1927,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/runtime.ts#L287">runtime.ts:287</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/web/src/runtime.ts#L287">runtime.ts:287</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index a7de239d95..b8fa2904be 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/a7a198048/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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 301495352b..d104828ff1 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/a7a198048/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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 9386bda536..257577e683 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/a7a198048/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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/a7a198048/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f79e4ebf3/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 c2a7b9c88e..5a668ee98c 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 b8d2dbeac3..1847192931 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:31.761</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:30.760</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:31.754</p></td>
+<td><p>00:30.753</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 2c9ce6cb35..c0da6e5435 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -588,7 +588,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 34.14s!
+resnet18_v1 inference graph built in 32.77s!
</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 266bd3fa6e..520ef4770a 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -606,7 +606,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 22.95s!
+yolov3-tiny inference graph built in 22.39s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 1189f7666e..076ce92b54 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:41.356</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:39.289</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -353,12 +353,12 @@
<col style="width: 7%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:51.028</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
+<td><p>00:49.743</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:50.328</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
+<td><p>00:49.546</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 f82260550f..69c0858439 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.234</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.203</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.745</p></td>
+<td><p>00:02.728</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>00:00.489</p></td>
+<td><p>00:00.475</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 55b212c429..749a0448d9 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.828</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.816</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.429</p></td>
+<td><p>00:00.421</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.399</p></td>
+<td><p>00:00.395</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 d796122979..9f96127d5c 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -497,6 +497,9 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
+</pre></div>
+</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -574,7 +577,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 98.360 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.781 ms
</pre></div>
</div>
</div>
@@ -646,7 +649,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 27.679 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 36.897 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 c055b78f7e..4858484bae 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -685,16 +685,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 11.06/11.06 result: MeasureResult(costs=(0.024268704999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6355149745941162, timestamp=1681197560.3814583) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
-No: 2 GFLOPS: 3.22/11.06 result: MeasureResult(costs=(0.0834299428,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.581608772277832, timestamp=1681197563.2382274) [('tile_y', [-1, 16]), ('tile_x', [-1, 4])],None,24
-No: 3 GFLOPS: 12.54/12.54 result: MeasureResult(costs=(0.0214062574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6045653820037842, timestamp=1681197565.1039245) [('tile_y', [-1, 16]), ('tile_x', [-1, 512])],None,94
-No: 4 GFLOPS: 1.51/12.54 result: MeasureResult(costs=(0.17822883260000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.060458183288574, timestamp=1681197568.2109227) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
-No: 5 GFLOPS: 3.88/12.54 result: MeasureResult(costs=(0.0692695088,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.362046480178833, timestamp=1681197569.6863804) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
-No: 6 GFLOPS: 11.35/12.54 result: MeasureResult(costs=(0.0236502174,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6270618438720703, timestamp=1681197570.331723) [('tile_y', [-1, 256]), ('tile_x', [-1, 512])],None,98
-No: 7 GFLOPS: 3.79/12.54 result: MeasureResult(costs=(0.0707499488,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3853721618652344, timestamp=1681197573.0042627) [('tile_y', [-1, 8]), ('tile_x', [-1, 8])],None,33
-No: 8 GFLOPS: 3.07/12.54 result: MeasureResult(costs=(0.08754015000000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6451199054718018, timestamp=1681197574.6616476) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
-No: 9 GFLOPS: 11.16/12.54 result: MeasureResult(costs=(0.024050462,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6092183589935303, timestamp=1681197575.3859806) [('tile_y', [-1, 256]), ('tile_x', [-1, 32])],None,58
-No: 10 GFLOPS: 3.02/12.54 result: MeasureResult(costs=(0.0887491358,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6393957138061523, timestamp=1681197577.0684767) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 1.52/1.52 result: MeasureResult(costs=(0.17712990560000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.088336229324341, timestamp=1681202515.178741) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
+No: 2 GFLOPS: 12.85/12.85 result: MeasureResult(costs=(0.0208879486,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6977832317352295, timestamp=1681202515.7725067) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+No: 3 GFLOPS: 3.33/12.85 result: MeasureResult(costs=(0.08067693719999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.551457166671753, timestamp=1681202518.5617752) [('tile_y', [-1, 64]), ('tile_x', [-1, 8])],None,36
+No: 4 GFLOPS: 0.88/12.85 result: MeasureResult(costs=(0.3056937464,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.128290176391602, timestamp=1681202523.7079847) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+No: 5 GFLOPS: 1.50/12.85 result: MeasureResult(costs=(0.1786422818,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.1030025482177734, timestamp=1681202526.9487379) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+No: 6 GFLOPS: 0.51/12.85 result: MeasureResult(costs=(0.5311725566,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.755533218383789, timestamp=1681202536.9443994) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
+No: 7 GFLOPS: 11.78/12.85 result: MeasureResult(costs=(0.022787891400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6363482475280762, timestamp=1681202538.8158693) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
+No: 8 GFLOPS: 4.53/12.85 result: MeasureResult(costs=(0.059290734,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2143659591674805, timestamp=1681202540.0241356) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
+No: 9 GFLOPS: 3.06/12.85 result: MeasureResult(costs=(0.08760568839999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6502587795257568, timestamp=1681202541.7958884) [('tile_y', [-1, 2]), ('tile_x', [-1, 16])],None,41
+No: 10 GFLOPS: 11.72/12.85 result: MeasureResult(costs=(0.022899041399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6210606098175049, timestamp=1681202542.4202776) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
</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 1728c8e6a9..da36f37349 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -563,7 +563,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 485.39099493000094, 'median': 485.2391821500021, 'std': 1.1640439743505182}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 508.9282783900012, 'median': 509.54074805000573, 'std': 1.5907018118433454}
</pre></div>
</div>
</div>
@@ -715,179 +715,179 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 21.72/ 21.72 GFLOPS | Progress: (4/20) | 10.98 s
-[Task 1/25] Current/Best: 9.44/ 21.89 GFLOPS | Progress: (8/20) | 15.79 s
-[Task 1/25] Current/Best: 9.45/ 21.89 GFLOPS | Progress: (12/20) | 17.97 s
-[Task 1/25] Current/Best: 7.02/ 23.77 GFLOPS | Progress: (16/20) | 20.00 s
-[Task 1/25] Current/Best: 5.75/ 23.77 GFLOPS | Progress: (20/20) | 22.42 s Done.
+[Task 1/25] Current/Best: 8.34/ 23.16 GFLOPS | Progress: (4/20) | 10.93 s
+[Task 1/25] Current/Best: 3.19/ 23.16 GFLOPS | Progress: (8/20) | 15.25 s
+[Task 1/25] Current/Best: 7.07/ 23.16 GFLOPS | Progress: (12/20) | 20.74 s
+[Task 1/25] Current/Best: 14.14/ 23.16 GFLOPS | Progress: (16/20) | 24.75 s
+[Task 1/25] Current/Best: 16.88/ 23.79 GFLOPS | Progress: (20/20) | 27.46 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 3.17/ 20.34 GFLOPS | Progress: (4/20) | 4.19 s
-[Task 2/25] Current/Best: 18.43/ 20.77 GFLOPS | Progress: (8/20) | 6.25 s
-[Task 2/25] Current/Best: 7.48/ 20.77 GFLOPS | Progress: (12/20) | 8.23 s
-[Task 2/25] Current/Best: 19.59/ 20.77 GFLOPS | Progress: (16/20) | 9.88 s
-[Task 2/25] Current/Best: 15.72/ 20.77 GFLOPS | Progress: (20/20) | 11.86 s Done.
+[Task 2/25] Current/Best: 16.17/ 16.97 GFLOPS | Progress: (4/20) | 4.38 s
+[Task 2/25] Current/Best: 13.04/ 16.97 GFLOPS | Progress: (8/20) | 6.44 s
+[Task 2/25] Current/Best: 22.07/ 22.07 GFLOPS | Progress: (12/20) | 8.40 s
+[Task 2/25] Current/Best: 6.12/ 22.07 GFLOPS | Progress: (16/20) | 10.38 s
+[Task 2/25] Current/Best: 5.47/ 22.07 GFLOPS | Progress: (20/20) | 11.97 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 23.74/ 23.74 GFLOPS | Progress: (4/20) | 4.98 s
-[Task 3/25] Current/Best: 6.32/ 24.68 GFLOPS | Progress: (8/20) | 7.73 s
-[Task 3/25] Current/Best: 14.68/ 24.68 GFLOPS | Progress: (12/20) | 9.98 s
-[Task 3/25] Current/Best: 22.55/ 24.68 GFLOPS | Progress: (16/20) | 12.85 s
-[Task 3/25] Current/Best: 7.97/ 24.68 GFLOPS | Progress: (20/20) | 15.24 s Done.
+[Task 3/25] Current/Best: 12.20/ 14.36 GFLOPS | Progress: (4/20) | 5.38 s
+[Task 3/25] Current/Best: 12.53/ 20.22 GFLOPS | Progress: (8/20) | 9.61 s
+[Task 3/25] Current/Best: 8.43/ 20.22 GFLOPS | Progress: (12/20) | 12.18 s
+[Task 3/25] Current/Best: 17.25/ 20.22 GFLOPS | Progress: (16/20) | 14.88 s
+[Task 3/25] Current/Best: 8.41/ 20.22 GFLOPS | Progress: (20/20) | 17.46 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 11.94/ 16.21 GFLOPS | Progress: (4/20) | 7.57 s
-[Task 4/25] Current/Best: 11.11/ 22.87 GFLOPS | Progress: (8/20) | 9.16 s
-[Task 4/25] Current/Best: 10.29/ 22.87 GFLOPS | Progress: (12/20) | 20.33 s
-[Task 4/25] Current/Best: 9.19/ 22.87 GFLOPS | Progress: (16/20) | 28.04 s
-[Task 4/25] Current/Best: 10.18/ 22.87 GFLOPS | Progress: (20/20) | 30.18 s
+[Task 4/25] Current/Best: 15.59/ 15.59 GFLOPS | Progress: (4/20) | 4.82 s
+[Task 4/25] Current/Best: 8.55/ 16.22 GFLOPS | Progress: (8/20) | 9.98 s
+[Task 4/25] Current/Best: 15.06/ 16.22 GFLOPS | Progress: (12/20) | 12.10 s
+[Task 4/25] Current/Best: 17.46/ 22.81 GFLOPS | Progress: (16/20) | 16.29 s
+[Task 4/25] Current/Best: 13.21/ 22.81 GFLOPS | Progress: (20/20) | 18.88 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 20.89/ 20.89 GFLOPS | Progress: (4/20) | 5.42 s
-[Task 5/25] Current/Best: 18.14/ 20.89 GFLOPS | Progress: (8/20) | 7.22 s
-[Task 5/25] Current/Best: 14.07/ 20.89 GFLOPS | Progress: (12/20) | 10.99 s
-[Task 5/25] Current/Best: 3.99/ 20.89 GFLOPS | Progress: (16/20) | 13.35 s
-[Task 5/25] Current/Best: 14.16/ 20.89 GFLOPS | Progress: (20/20) | 15.31 s Done.
+[Task 5/25] Current/Best: 19.44/ 23.25 GFLOPS | Progress: (4/20) | 4.34 s
+[Task 5/25] Current/Best: 21.13/ 23.25 GFLOPS | Progress: (8/20) | 6.30 s
+[Task 5/25] Current/Best: 3.02/ 23.25 GFLOPS | Progress: (12/20) | 9.08 s
+[Task 5/25] Current/Best: 15.83/ 23.25 GFLOPS | Progress: (16/20) | 11.63 s
+[Task 5/25] Current/Best: 18.04/ 23.25 GFLOPS | Progress: (20/20) | 13.71 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 11.97/ 17.90 GFLOPS | Progress: (4/20) | 5.13 s
-[Task 6/25] Current/Best: 14.49/ 17.90 GFLOPS | Progress: (8/20) | 8.36 s
-[Task 6/25] Current/Best: 16.44/ 17.90 GFLOPS | Progress: (12/20) | 11.57 s
-[Task 6/25] Current/Best: 7.31/ 17.90 GFLOPS | Progress: (16/20) | 14.51 s Done.
-
-[Task 6/25] Current/Best: 12.24/ 17.90 GFLOPS | Progress: (20/20) | 17.19 s Done.
+[Task 6/25] Current/Best: 11.17/ 14.49 GFLOPS | Progress: (4/20) | 5.19 s
+[Task 6/25] Current/Best: 8.76/ 14.49 GFLOPS | Progress: (8/20) | 8.03 s
+[Task 6/25] Current/Best: 14.73/ 17.87 GFLOPS | Progress: (12/20) | 10.71 s
+[Task 6/25] Current/Best: 12.98/ 17.87 GFLOPS | Progress: (16/20) | 12.81 s
+[Task 6/25] Current/Best: 9.61/ 17.87 GFLOPS | Progress: (20/20) | 19.52 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 6.31/ 14.75 GFLOPS | Progress: (4/20) | 5.55 s
-[Task 7/25] Current/Best: 12.23/ 16.49 GFLOPS | Progress: (8/20) | 8.53 s
-[Task 7/25] Current/Best: 13.25/ 22.42 GFLOPS | Progress: (12/20) | 10.99 s
-[Task 7/25] Current/Best: 15.87/ 22.42 GFLOPS | Progress: (16/20) | 13.40 s
-[Task 7/25] Current/Best: 3.10/ 22.42 GFLOPS | Progress: (20/20) | 16.38 s Done.
+[Task 7/25] Current/Best: 15.75/ 15.75 GFLOPS | Progress: (4/20) | 5.77 s
+[Task 7/25] Current/Best: 5.77/ 15.75 GFLOPS | Progress: (8/20) | 8.79 s
+[Task 7/25] Current/Best: 7.16/ 17.87 GFLOPS | Progress: (12/20) | 11.38 s
+[Task 7/25] Current/Best: 12.28/ 18.17 GFLOPS | Progress: (16/20) | 14.26 s
+[Task 7/25] Current/Best: 14.73/ 19.94 GFLOPS | Progress: (20/20) | 16.46 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 11.83/ 17.98 GFLOPS | Progress: (4/20) | 5.41 s
-[Task 8/25] Current/Best: 12.81/ 17.98 GFLOPS | Progress: (8/20) | 8.41 s
-[Task 8/25] Current/Best: 13.09/ 17.98 GFLOPS | Progress: (12/20) | 11.01 s
-[Task 8/25] Current/Best: 10.49/ 21.30 GFLOPS | Progress: (16/20) | 13.06 s
-[Task 8/25] Current/Best: 6.39/ 21.30 GFLOPS | Progress: (20/20) | 16.51 s Done.
+[Task 8/25] Current/Best: 13.81/ 13.93 GFLOPS | Progress: (4/20) | 5.40 s
+[Task 8/25] Current/Best: 13.00/ 13.93 GFLOPS | Progress: (8/20) | 10.14 s
+[Task 8/25] Current/Best: 14.84/ 14.84 GFLOPS | Progress: (12/20) | 21.83 s
+[Task 8/25] Current/Best: 4.96/ 16.07 GFLOPS | Progress: (16/20) | 30.54 s
+[Task 8/25] Current/Best: 2.70/ 16.07 GFLOPS | Progress: (20/20) | 34.28 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 12.80/ 21.22 GFLOPS | Progress: (4/20) | 4.37 s
-[Task 9/25] Current/Best: 21.42/ 21.42 GFLOPS | Progress: (8/20) | 6.28 s
-[Task 9/25] Current/Best: 18.08/ 21.42 GFLOPS | Progress: (12/20) | 11.42 s
-[Task 9/25] Current/Best: 11.26/ 21.42 GFLOPS | Progress: (16/20) | 14.47 s
-[Task 9/25] Current/Best: 20.29/ 21.44 GFLOPS | Progress: (20/20) | 16.08 s Done.
+[Task 9/25] Current/Best: 5.43/ 12.18 GFLOPS | Progress: (4/20) | 5.20 s
+[Task 9/25] Current/Best: 11.07/ 16.51 GFLOPS | Progress: (8/20) | 10.82 s
+[Task 9/25] Current/Best: 13.99/ 23.03 GFLOPS | Progress: (12/20) | 12.85 s
+[Task 9/25] Current/Best: 17.58/ 23.03 GFLOPS | Progress: (16/20) | 17.69 s
+[Task 9/25] Current/Best: 3.24/ 23.03 GFLOPS | Progress: (20/20) | 21.82 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 10.28/ 18.02 GFLOPS | Progress: (4/20) | 5.28 s
-[Task 10/25] Current/Best: 21.55/ 21.55 GFLOPS | Progress: (8/20) | 7.01 s
-[Task 10/25] Current/Best: 16.53/ 21.55 GFLOPS | Progress: (12/20) | 9.20 s
-[Task 10/25] Current/Best: 19.73/ 21.55 GFLOPS | Progress: (16/20) | 12.88 s
-[Task 10/25] Current/Best: 7.71/ 21.55 GFLOPS | Progress: (20/20) | 14.59 s Done.
+[Task 10/25] Current/Best: 13.26/ 18.93 GFLOPS | Progress: (4/20) | 5.15 s
+[Task 10/25] Current/Best: 14.07/ 18.93 GFLOPS | Progress: (8/20) | 8.34 s
+[Task 10/25] Current/Best: 8.07/ 18.93 GFLOPS | Progress: (12/20) | 10.42 s
+[Task 10/25] Current/Best: 15.59/ 18.93 GFLOPS | Progress: (16/20) | 12.49 s
+[Task 10/25] Current/Best: 2.51/ 18.93 GFLOPS | Progress: (20/20) | 14.47 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 19.51/ 20.45 GFLOPS | Progress: (4/20) | 5.01 s
-[Task 11/25] Current/Best: 14.46/ 20.45 GFLOPS | Progress: (8/20) | 8.14 s
-[Task 11/25] Current/Best: 18.90/ 20.45 GFLOPS | Progress: (12/20) | 10.99 s
-[Task 11/25] Current/Best: 17.15/ 21.64 GFLOPS | Progress: (16/20) | 13.45 s
-[Task 11/25] Current/Best: 22.19/ 22.19 GFLOPS | Progress: (20/20) | 16.39 s Done.
+[Task 11/25] Current/Best: 7.81/ 23.18 GFLOPS | Progress: (4/20) | 6.25 s
+[Task 11/25] Current/Best: 14.57/ 23.18 GFLOPS | Progress: (8/20) | 8.81 s
+[Task 11/25] Current/Best: 17.56/ 23.18 GFLOPS | Progress: (12/20) | 11.82 s
+[Task 11/25] Current/Best: 7.04/ 23.18 GFLOPS | Progress: (16/20) | 14.60 s
+[Task 11/25] Current/Best: 12.87/ 23.18 GFLOPS | Progress: (20/20) | 17.18 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 12.92/ 21.79 GFLOPS | Progress: (4/20) | 5.19 s
-[Task 12/25] Current/Best: 13.48/ 21.79 GFLOPS | Progress: (8/20) | 8.80 s
-[Task 12/25] Current/Best: 5.06/ 21.79 GFLOPS | Progress: (12/20) | 13.65 s
-[Task 12/25] Current/Best: 12.05/ 21.79 GFLOPS | Progress: (16/20) | 17.64 s
-[Task 12/25] Current/Best: 8.50/ 21.79 GFLOPS | Progress: (20/20) | 20.69 s Done.
+[Task 12/25] Current/Best: 4.45/ 12.60 GFLOPS | Progress: (4/20) | 6.53 s
+[Task 12/25] Current/Best: 14.27/ 20.89 GFLOPS | Progress: (8/20) | 8.58 s
+[Task 12/25] Current/Best: 10.13/ 20.89 GFLOPS | Progress: (12/20) | 12.05 s
+[Task 12/25] Current/Best: 13.98/ 20.89 GFLOPS | Progress: (16/20) | 14.50 s
+[Task 12/25] Current/Best: 9.12/ 22.12 GFLOPS | Progress: (20/20) | 18.54 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 15.49/ 15.49 GFLOPS | Progress: (4/20) | 5.96 s
-[Task 13/25] Current/Best: 9.09/ 15.49 GFLOPS | Progress: (8/20) | 8.59 s
-[Task 13/25] Current/Best: 17.69/ 17.69 GFLOPS | Progress: (12/20) | 12.09 s
-[Task 13/25] Current/Best: 16.68/ 18.59 GFLOPS | Progress: (16/20) | 15.99 s
-[Task 13/25] Current/Best: 16.62/ 18.59 GFLOPS | Progress: (20/20) | 18.79 s Done.
+[Task 13/25] Current/Best: 11.46/ 12.10 GFLOPS | Progress: (4/20) | 6.94 s
+[Task 13/25] Current/Best: 17.75/ 17.75 GFLOPS | Progress: (8/20) | 9.26 s
+[Task 13/25] Current/Best: 14.14/ 22.81 GFLOPS | Progress: (12/20) | 11.35 s
+[Task 13/25] Current/Best: 17.22/ 22.81 GFLOPS | Progress: (16/20) | 14.27 s
+[Task 13/25] Current/Best: 15.04/ 22.81 GFLOPS | Progress: (20/20) | 16.54 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 15.52/ 16.31 GFLOPS | Progress: (4/20) | 6.39 s
-[Task 14/25] Current/Best: 15.35/ 16.31 GFLOPS | Progress: (8/20) | 8.88 s
-[Task 14/25] Current/Best: 15.48/ 16.31 GFLOPS | Progress: (12/20) | 13.87 s
-[Task 14/25] Current/Best: 10.52/ 16.31 GFLOPS | Progress: (16/20) | 17.78 s
-[Task 14/25] Current/Best: 10.11/ 18.18 GFLOPS | Progress: (20/20) | 19.95 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.37/ 19.99 GFLOPS | Progress: (4/20) | 6.36 s
-[Task 15/25] Current/Best: 12.58/ 19.99 GFLOPS | Progress: (8/20) | 9.20 s
-[Task 15/25] Current/Best: 15.57/ 20.30 GFLOPS | Progress: (12/20) | 11.21 s
-[Task 15/25] Current/Best: 18.69/ 20.30 GFLOPS | Progress: (16/20) | 12.80 s
-[Task 15/25] Current/Best: 18.69/ 20.30 GFLOPS | Progress: (20/20) | 15.10 s Done.
-
+[Task 14/25] Current/Best: 14.20/ 14.20 GFLOPS | Progress: (4/20) | 5.48 s
+[Task 14/25] Current/Best: 13.27/ 14.20 GFLOPS | Progress: (8/20) | 11.16 s
+[Task 14/25] Current/Best: 12.96/ 14.48 GFLOPS | Progress: (12/20) | 12.87 s
+[Task 14/25] Current/Best: 18.40/ 18.40 GFLOPS | Progress: (16/20) | 16.50 s
+[Task 14/25] Current/Best: 11.00/ 18.40 GFLOPS | Progress: (20/20) | 20.07 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
+[Task 15/25] Current/Best: 12.06/ 21.20 GFLOPS | Progress: (4/20) | 7.09 s
+[Task 15/25] Current/Best: 6.37/ 21.20 GFLOPS | Progress: (8/20) | 9.95 s
+[Task 15/25] Current/Best: 12.88/ 21.20 GFLOPS | Progress: (12/20) | 11.82 s
+[Task 15/25] Current/Best: 9.56/ 21.20 GFLOPS | Progress: (16/20) | 15.46 s
+[Task 15/25] Current/Best: 9.82/ 21.20 GFLOPS | Progress: (20/20) | 18.15 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 9.61/ 17.76 GFLOPS | Progress: (4/20) | 4.86 s
-[Task 16/25] Current/Best: 19.04/ 19.87 GFLOPS | Progress: (8/20) | 7.92 s
-[Task 16/25] Current/Best: 4.34/ 19.87 GFLOPS | Progress: (12/20) | 9.75 s
-[Task 16/25] Current/Best: 5.19/ 19.87 GFLOPS | Progress: (16/20) | 11.53 s
-[Task 16/25] Current/Best: 17.90/ 19.87 GFLOPS | Progress: (20/20) | 13.25 s Done.
+[Task 16/25] Current/Best: 19.24/ 19.24 GFLOPS | Progress: (4/20) | 4.82 s
+[Task 16/25] Current/Best: 15.64/ 19.24 GFLOPS | Progress: (8/20) | 6.60 s
+[Task 16/25] Current/Best: 9.11/ 19.24 GFLOPS | Progress: (12/20) | 8.92 s
+[Task 16/25] Current/Best: 13.74/ 19.95 GFLOPS | Progress: (16/20) | 10.71 s
+[Task 16/25] Current/Best: 9.30/ 19.95 GFLOPS | Progress: (20/20) | 12.27 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 21.49/ 21.49 GFLOPS | Progress: (4/20) | 5.04 s
-[Task 17/25] Current/Best: 10.14/ 21.49 GFLOPS | Progress: (8/20) | 7.52 s
-[Task 17/25] Current/Best: 12.90/ 21.49 GFLOPS | Progress: (12/20) | 10.22 s
-[Task 17/25] Current/Best: 9.88/ 21.49 GFLOPS | Progress: (16/20) | 12.69 s
-[Task 17/25] Current/Best: 16.10/ 21.49 GFLOPS | Progress: (20/20) | 15.52 s Done.
+[Task 17/25] Current/Best: 12.82/ 22.48 GFLOPS | Progress: (4/20) | 4.91 s
+[Task 17/25] Current/Best: 6.11/ 22.48 GFLOPS | Progress: (8/20) | 7.96 s
+[Task 17/25] Current/Best: 11.70/ 22.48 GFLOPS | Progress: (12/20) | 10.54 s
+[Task 17/25] Current/Best: 19.60/ 22.48 GFLOPS | Progress: (16/20) | 12.80 s
+[Task 17/25] Current/Best: 7.00/ 23.20 GFLOPS | Progress: (20/20) | 15.80 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 20.26/ 20.26 GFLOPS | Progress: (4/20) | 4.73 s
-[Task 18/25] Current/Best: 10.87/ 20.26 GFLOPS | Progress: (8/20) | 7.30 s
-[Task 18/25] Current/Best: 11.91/ 20.26 GFLOPS | Progress: (12/20) | 9.89 s
-[Task 18/25] Current/Best: 12.33/ 20.26 GFLOPS | Progress: (16/20) | 13.57 s
-[Task 18/25] Current/Best: 18.21/ 20.26 GFLOPS | Progress: (20/20) | 15.84 s Done.
+[Task 18/25] Current/Best: 15.02/ 19.13 GFLOPS | Progress: (4/20) | 6.11 s
+[Task 18/25] Current/Best: 16.20/ 20.33 GFLOPS | Progress: (8/20) | 8.32 s
+[Task 18/25] Current/Best: 15.35/ 21.15 GFLOPS | Progress: (12/20) | 10.86 s
+[Task 18/25] Current/Best: 7.02/ 21.15 GFLOPS | Progress: (16/20) | 14.61 s
+[Task 18/25] Current/Best: 10.44/ 21.15 GFLOPS | Progress: (20/20) | 17.97 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 18.06/ 18.14 GFLOPS | Progress: (4/20) | 6.16 s
-[Task 19/25] Current/Best: 9.36/ 18.14 GFLOPS | Progress: (8/20) | 9.93 s
-[Task 19/25] Current/Best: 8.66/ 18.48 GFLOPS | Progress: (12/20) | 12.96 s
-[Task 19/25] Current/Best: 4.76/ 22.29 GFLOPS | Progress: (16/20) | 18.15 s
-[Task 19/25] Current/Best: 10.59/ 22.29 GFLOPS | Progress: (20/20) | 21.97 s Done.
+[Task 19/25] Current/Best: 11.86/ 11.86 GFLOPS | Progress: (4/20) | 5.93 s
+[Task 19/25] Current/Best: 7.40/ 17.02 GFLOPS | Progress: (8/20) | 8.95 s
+[Task 19/25] Current/Best: 10.72/ 19.65 GFLOPS | Progress: (12/20) | 11.63 s
+[Task 19/25] Current/Best: 11.09/ 19.65 GFLOPS | Progress: (16/20) | 15.17 s
+[Task 19/25] Current/Best: 15.56/ 19.65 GFLOPS | Progress: (20/20) | 18.84 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 16.96/ 20.79 GFLOPS | Progress: (4/20) | 5.34 s
-[Task 20/25] Current/Best: 5.37/ 20.79 GFLOPS | Progress: (8/20) | 9.07 s
-[Task 20/25] Current/Best: 14.04/ 20.79 GFLOPS | Progress: (12/20) | 11.34 s
-[Task 20/25] Current/Best: 18.80/ 20.79 GFLOPS | Progress: (16/20) | 13.50 s
-[Task 20/25] Current/Best: 13.99/ 20.79 GFLOPS | Progress: (20/20) | 16.72 s
+[Task 20/25] Current/Best: 9.67/ 19.88 GFLOPS | Progress: (4/20) | 4.77 s
+[Task 20/25] Current/Best: 16.47/ 19.88 GFLOPS | Progress: (8/20) | 8.01 s
+[Task 20/25] Current/Best: 6.20/ 19.88 GFLOPS | Progress: (12/20) | 11.20 s
+[Task 20/25] Current/Best: 16.93/ 19.88 GFLOPS | Progress: (16/20) | 14.57 s
+[Task 20/25] Current/Best: 16.94/ 19.88 GFLOPS | Progress: (20/20) | 17.39 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-[Task 21/25] Current/Best: 19.26/ 22.24 GFLOPS | Progress: (4/20) | 5.56 s
-[Task 21/25] Current/Best: 9.36/ 22.24 GFLOPS | Progress: (8/20) | 9.05 s
-[Task 21/25] Current/Best: 14.14/ 22.24 GFLOPS | Progress: (12/20) | 11.95 s
-[Task 21/25] Current/Best: 14.69/ 22.24 GFLOPS | Progress: (16/20) | 13.82 s
-[Task 21/25] Current/Best: 6.40/ 22.24 GFLOPS | Progress: (20/20) | 16.44 s
+[Task 21/25] Current/Best: 14.48/ 14.48 GFLOPS | Progress: (4/20) | 5.62 s
+[Task 21/25] Current/Best: 9.28/ 14.48 GFLOPS | Progress: (8/20) | 8.62 s
+[Task 21/25] Current/Best: 15.96/ 17.99 GFLOPS | Progress: (12/20) | 11.08 s
+[Task 21/25] Current/Best: 18.70/ 18.70 GFLOPS | Progress: (16/20) | 13.90 s
+[Task 21/25] Current/Best: 18.13/ 19.65 GFLOPS | Progress: (20/20) | 17.40 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 12.04/ 12.79 GFLOPS | Progress: (4/20) | 7.64 s
-[Task 22/25] Current/Best: 3.12/ 23.40 GFLOPS | Progress: (8/20) | 10.52 s
-[Task 22/25] Current/Best: 19.24/ 23.40 GFLOPS | Progress: (12/20) | 12.35 s
-[Task 22/25] Current/Best: 17.41/ 23.40 GFLOPS | Progress: (16/20) | 14.34 s
-[Task 22/25] Current/Best: 7.83/ 23.40 GFLOPS | Progress: (20/20) | 16.30 s Done.
+[Task 22/25] Current/Best: 2.70/ 7.49 GFLOPS | Progress: (4/20) | 5.26 s
+[Task 22/25] Current/Best: 17.82/ 19.95 GFLOPS | Progress: (8/20) | 7.01 s
+[Task 22/25] Current/Best: 10.67/ 19.95 GFLOPS | Progress: (12/20) | 8.75 s
+[Task 22/25] Current/Best: 17.76/ 23.01 GFLOPS | Progress: (16/20) | 10.48 s
+[Task 22/25] Current/Best: 13.74/ 23.01 GFLOPS | Progress: (20/20) | 12.80 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 5.44/ 22.49 GFLOPS | Progress: (4/20) | 6.06 s
-[Task 23/25] Current/Best: 6.23/ 22.49 GFLOPS | Progress: (8/20) | 9.85 s
-[Task 23/25] Current/Best: 19.36/ 22.49 GFLOPS | Progress: (12/20) | 13.65 s
-[Task 23/25] Current/Best: 5.44/ 22.49 GFLOPS | Progress: (16/20) | 16.34 s
-[Task 23/25] Current/Best: 2.71/ 22.49 GFLOPS | Progress: (20/20) | 20.60 s Done.
+[Task 23/25] Current/Best: 8.82/ 23.47 GFLOPS | Progress: (4/20) | 5.90 s
+[Task 23/25] Current/Best: 1.55/ 23.47 GFLOPS | Progress: (8/20) | 10.09 s
+[Task 23/25] Current/Best: 3.08/ 23.47 GFLOPS | Progress: (12/20) | 13.29 s
+[Task 23/25] Current/Best: 10.32/ 23.47 GFLOPS | Progress: (16/20) | 16.68 s
+[Task 23/25] Current/Best: 13.60/ 23.47 GFLOPS | Progress: (20/20) | 19.45 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 10.22/ 10.22 GFLOPS | Progress: (4/20) | 13.78 s
-[Task 24/25] Current/Best: 9.24/ 10.22 GFLOPS | Progress: (8/20) | 26.12 s
-[Task 24/25] Current/Best: 0.61/ 10.22 GFLOPS | Progress: (12/20) | 30.32 s
-[Task 24/25] Current/Best: 8.09/ 10.22 GFLOPS | Progress: (16/20) | 40.68 s
-[Task 24/25] Current/Best: 1.22/ 10.22 GFLOPS | Progress: (20/20) | 53.36 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+[Task 24/25] Current/Best: 4.92/ 4.92 GFLOPS | Progress: (4/20) | 13.13 s
+[Task 24/25] Current/Best: 1.13/ 4.92 GFLOPS | Progress: (8/20) | 24.13 s
+[Task 24/25] Current/Best: 4.74/ 4.92 GFLOPS | Progress: (12/20) | 35.10 s
+[Task 24/25] Current/Best: 9.57/ 9.57 GFLOPS | Progress: (16/20) | 47.35 s
+[Task 24/25] Current/Best: 3.28/ 9.57 GFLOPS | Progress: (20/20) | 58.30 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 3.21/ 8.15 GFLOPS | Progress: (4/20) | 7.68 s
+[Task 25/25] Current/Best: 1.55/ 8.15 GFLOPS | Progress: (8/20) | 9.18 s Done.
+ Done.
Done.
-[Task 25/25] Current/Best: 1.55/ 6.03 GFLOPS | Progress: (4/20) | 5.99 s
-[Task 25/25] Current/Best: 5.96/ 6.03 GFLOPS | Progress: (8/20) | 16.96 s
-[Task 25/25] Current/Best: 5.95/ 8.17 GFLOPS | Progress: (12/20) | 27.93 s
-[Task 25/25] Current/Best: 8.33/ 8.33 GFLOPS | Progress: (16/20) | 31.88 s
-[Task 25/25] Current/Best: 2.77/ 8.33 GFLOPS | Progress: (20/20) | 37.50 s
+[Task 25/25] Current/Best: 1.55/ 8.27 GFLOPS | Progress: (12/20) | 11.03 s
+[Task 25/25] Current/Best: 3.23/ 8.27 GFLOPS | Progress: (16/20) | 22.03 s
+[Task 25/25] Current/Best: 3.50/ 8.27 GFLOPS | Progress: (20/20) | 34.42 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -948,7 +948,7 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621102
class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -986,8 +986,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 405.78551404999644, 'median': 405.6996923999918, 'std': 0.9185659256848557}
-unoptimized: {'mean': 485.39099493000094, 'median': 485.2391821500021, 'std': 1.1640439743505182}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 408.6111357099958, 'median': 409.75637514999335, 'std': 4.784204697403965}
+unoptimized: {'mean': 508.9282783900012, 'median': 509.54074805000573, 'std': 1.5907018118433454}
</pre></div>
</div>
</div>
@@ -1001,7 +1001,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 59.755 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 20.379 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 6ecc6028ed..c078153321 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -543,7 +543,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.336e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.342e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 16492262b6..1029f2cfcb 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -513,7 +513,7 @@ class Module:
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x231293b0)), stage(b, placeholder(b, 0x2a176010)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attr [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x9817330)), stage(b, placeholder(b, 0x113acf10)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index 0511c2fcd2..fca15cd4b3 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:31.903</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>16:15.802</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,35 +354,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>11:59.755</p></td>
+<td><p>12:20.379</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>01:27.679</p></td>
+<td><p>01:36.897</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>01:00.899</p></td>
+<td><p>01:02.267</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:37.283</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
+<td><p>00:36.942</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:23.889</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
+<td><p>00:36.624</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>00:01.362</p></td>
+<td><p>00:01.656</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>00:00.860</p></td>
+<td><p>00:00.871</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>00:00.175</p></td>
+<td><p>00:00.166</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 3101c066d7..01a76f1bdd 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -610,7 +610,7 @@ 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>
@@ -649,7 +649,7 @@ factor to be the number of threads on your CPU.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000026
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000034
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -686,10 +686,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.77233000007982e-06 1.0
- naive 6.696499999999999e-06 0.8615820481028506
-parallel 6.9913e-06 0.8995114720975822
- vector 2.6369700000000003e-05 3.3927663904812575
+ numpy 8.086299999376934e-06 1.0
+ naive 6.9577e-06 0.8604306049164767
+parallel 7.5797000000000005e-06 0.9373508280157837
+ vector 3.38113e-05 4.181306654787138
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1005,7 +1005,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018751
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018736
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1046,7 +1046,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.382162
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.506791
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1110,7 +1110,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.314402
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.301348
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1159,7 +1159,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.344549
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.336904
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1208,7 +1208,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116712
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.114751
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1278,7 +1278,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.107431
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108123
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1344,7 +1344,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111194
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111043
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1401,7 +1401,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146423
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146087
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1454,13 +1454,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.382161504 1.0
- blocking 0.3144017308 0.09295881655212643
- vectorization 0.34454892519999997 0.10187240461240847
-loop permutation 0.11671236069999999 0.034508216287710426
- array packing 0.10743148389999999 0.031764149575040514
- block caching 0.1111941343 0.03287664831158814
- parallelization 0.146422571 0.04329260173614702
+ none 3.5067909512 1.0
+ blocking 0.3013484693 0.08593282961360459
+ vectorization 0.3369037844 0.09607181867647795
+loop permutation 0.1147505066 0.03272236874021052
+ array packing 0.1081231563 0.030832506928592643
+ block caching 0.111042525 0.03166499701443623
+ parallelization 0.1460868507 0.04165827183111958
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1492,7 +1492,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.899 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.267 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>