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 2023/05/04 18:58:58 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@4d37a0a078435cd36c56112ee0ee21b3d6bb8bd0)
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 2fd147f91b deploying docs (apache/tvm@4d37a0a078435cd36c56112ee0ee21b3d6bb8bd0)
2fd147f91b is described below
commit 2fd147f91b8920e9572e0d1baabb9374a7bef5bf
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu May 4 18:58:51 2023 +0000
deploying docs (apache/tvm@4d37a0a078435cd36c56112ee0ee21b3d6bb8bd0)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 349354 -> 312563 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24292 -> 22858 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 | 699 ++++++++++++++++++---
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 137 ++--
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 331 ++++++++--
.../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 | 18 +-
.../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 | 16 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 4 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 60 +-
.../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 | 14 +-
docs/how_to/compile_models/from_pytorch.html | 13 +-
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 | 25 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 59 +-
docs/how_to/deploy_models/deploy_prequantized.html | 9 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
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 | 699 ++++++++++++++++++---
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 137 ++--
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 331 ++++++++--
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 | 18 +-
.../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 | 16 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
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 | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 278 ++++----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
130 files changed, 2785 insertions(+), 1303 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index b147d290fc..793f3e36e6 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 a474f132c9..94f0e4545f 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 4e37778632..3a3cab562e 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 24.094 seconds)
+ **Total running time of the script:** ( 1 minutes 25.129 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 ac6983b4b9..67853f3366 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.zipf1ab620a-377c-44b7-a2db-8c20125f8734 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip98fe92e9-da98-4da2-b68b-52f7ba8db68e 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 de82cc8a8f..d4b9974a09 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, 45.6MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 43.9MB/s]
51%|#####1 | 21.2M/41.5M [00:00<00:00, 53.1MB/s]
64%|######4 | 26.6M/41.5M [00:00<00:00, 46.2MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 43.7MB/s]
93%|#########2| 38.5M/41.5M [00:00<00:00, 37.4MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 41.5MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:00, 54.7MB/s]
28%|##7 | 11.5M/41.5M [00:00<00:00, 46.3MB/s]
39%|###8 | 16.0M/41.5M [00:00<00:00, 28.2MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.2MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 39.3MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 38.3MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
index 1eb2050b2e..32f99162fd 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]
30%|##9 | 13.3M/44.7M [00:00<00:00, 139MB/s]
59%|#####9 | 26.5M/44.7M [00:00<00:00, 86.0MB/s]
80%|######## | 35.8M/44.7M [00:00<00:00, 89.5MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 85.3MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
14%|#4 | 6.30M/44.7M [00:00<00:00, 56.8MB/s]
26%|##6 | 11.7M/44.7M [00:00<00:00, 53.5MB/s]
38%|###7 | 16.8M/44.7M [00:00<00:00, 39.5MB/s]
54%|#####3 | 24.1M/44.7M [00:00<00:00, 50.1MB/s]
68%|######7 | 30.3M/44.7M [00:00<00:00, 45.5MB/s]
78%|#######8 | 35.0M/44.7M [00:00<00:00, 44.3MB/s]
88%|########8 | 39.4M/44.7M [00:00<00:00, 42.6MB/s]
98%|#########7| 43.6M/44.7M [00:01<00:00, 31.8MB/s]
100%|##########| 44.7M/44.7M [00:01<00:00, 40.3MB/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 62cba2a9d3..96ba88dfef 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 31.816 seconds)
+ **Total running time of the script:** ( 1 minutes 30.016 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 156564e704..fc5e07acf2 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**06:59.655** total execution time for **how_to_compile_models** files:
+**07:02.123** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:31.816 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:30.016 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:24.094 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:25.129 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:59.034 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:57.752 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:39.219 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.942 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.758 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:33.631 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.428 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.288 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:28.962 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:30.105 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.166 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:27.214 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:24.461 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:25.228 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.717 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.820 | 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 fbdc647a69..4048a0bd33 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
@@ -673,7 +673,7 @@ 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)
- 2540.4115 2540.1485 2543.9367 2537.6377 1.7478
+ 2545.6327 2545.1691 2547.9848 2544.0202 1.3874
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 a2b5c22952..261f9caab4 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
5439488/102967424 [>.............................] - ETA: 1s
8380416/102967424 [=>............................] - ETA: 2s
16769024/102967424 [===>..........................] - ETA: 1s
24748032/102967424 [======>.......................] - ETA: 1s
25157632/102967424 [======>.......................] - ETA: 1s
33546240/102967424 [========>.....................] - ETA: 1s
40189952/102967424 [==========>...................] - ETA: 1s
41934848/102967424 [===========>..................] - ETA: 1s
50323456/102967424 [=============>................] - ETA: 0s
56967168/102967424 [===============>..............] - ETA: 0s
58712064/102967424 [================>.............] - ETA: 0s
65355776/102967424 [==================>...........] - ETA: 0s
67100672/102967424 [==================>...........] - ETA: 0s
69296128/102967424 [===================>..........] - ETA: 0s
75489280/102967424 [====================>.........] -
ETA: 0s
82124800/102967424 [======================>.......] - ETA: 0s
83877888/102967424 [=======================>......] - ETA: 0s
84017152/102967424 [=======================>......] - ETA: 0s
90521600/102967424 [=========================>....] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
99098624/102967424 [===========================>..] - ETA: 0s
100646912/102967424 [============================>.] - ETA: 0s
102850560/102967424
[============================>.] - ETA: 0s
102967424/102967424 [==============================] - 2s 0us/step
+
8192/102967424 [..............................] - ETA: 0s
8380416/102967424 [=>............................] - ETA: 0s
16769024/102967424 [===>..........................] - ETA: 0s
23396352/102967424 [=====>........................] - ETA: 0s
26484736/102967424 [======>.......................] - ETA: 0s
33546240/102967424 [========>.....................] - ETA: 0s
41934848/102967424 [===========>..................] - ETA: 0s
50323456/102967424 [=============>................] - ETA: 0s
58712064/102967424 [================>.............] - ETA: 0s
67100672/102967424 [==================>...........] - ETA: 0s
75489280/102967424 [====================>.........] - ETA: 0s
83877888/102967424 [=======================>......] - ETA: 0s
90521600/102967424 [=========================>....] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
100392960/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] -
1s 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 9861e85758..f67a68ba4d 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)
- 14.3295 14.2650 14.6626 14.1360 0.1888
+ 16.7394 16.5290 17.6822 16.3120 0.4470
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 c25f4e60e2..79da05e592 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<00:03, 48.6MB/s]
6%|6 | 10.9M/170M [00:00<00:04, 38.6MB/s]
9%|8 | 14.7M/170M [00:00<00:04, 37.1MB/s]
11%|# | 18.2M/170M [00:00<00:04, 34.1MB/s]
14%|#4 | 24.0M/170M [00:00<00:04, 35.4MB/s]
19%|#8 | 32.0M/170M [00:00<00:03, 36.9MB/s]
24%|##3 | 40.0M/170M [00:01<00:03, 40.7MB/s]
27%|##7 | 46.3M/170M [00:01<00:02, 43.8MB/s]
30%|##9 | 50.5M/170M [00:01<00:02, 42.6MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 43.9MB/s]
38%|###7 | 64.0M/170M [00:01<00:02, 47.1MB/s]
42%|####2 | 72.0M/170M [00:01<00:01, 54.8MB/s]
46%|####6 | 78.3M/170M [00:01<00:01, 52.2MB/s]
49%|####9 | 83.4M/170M [00:01<00:01, 49.4MB/s]
52%|#####1 | 88.2M/170M [00:02<00:02, 40.3MB/s]
57%|#####6 | 96.0M/170M [00:02<00:01, 43.0MB/s]
61%|######1 | 104M/170M [00:02<00:01, 41.9MB/s
]
66%|######5 | 112M/170M [00:02<00:01, 43.0MB/s]
71%|####### | 120M/170M [00:02<00:01, 47.5MB/s]
75%|#######5 | 128M/170M [00:03<00:00, 50.9MB/s]
80%|######## | 136M/170M [00:03<00:00, 40.8MB/s]
85%|########4 | 144M/170M [00:03<00:00, 45.9MB/s]
88%|########8 | 150M/170M [00:03<00:00, 47.0MB/s]
91%|#########1| 155M/170M [00:03<00:00, 46.5MB/s]
94%|#########4| 160M/170M [00:03<00:00, 39.7MB/s]
96%|#########6| 164M/170M [00:03<00:00, 38.3MB/s]
99%|#########8| 168M/170M [00:04<00:00, 39.4MB/s]
100%|##########| 170M/170M [00:04<00:00, 43.3MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:03, 46.9MB/s]
6%|6 | 10.8M/170M [00:00<00:04, 40.9MB/s]
9%|8 | 14.7M/170M [00:00<00:04, 35.7MB/s]
11%|# | 18.1M/170M [00:00<00:05, 31.4MB/s]
14%|#4 | 24.0M/170M [00:00<00:05, 27.7MB/s]
17%|#6 | 28.4M/170M [00:00<00:04, 31.6MB/s]
19%|#8 | 32.0M/170M [00:01<00:05, 28.9MB/s]
24%|##3 | 40.0M/170M [00:01<00:03, 36.0MB/s]
28%|##8 | 47.9M/170M [00:01<00:02, 46.3MB/s]
32%|###1 | 54.3M/170M [00:01<00:02, 51.3MB/s]
35%|###5 | 59.6M/170M [00:01<00:02, 47.4MB/s]
38%|###7 | 64.5M/170M [00:01<00:02, 42.6MB/s]
42%|####2 | 72.0M/170M [00:01<00:02, 42.9MB/s]
47%|####7 | 80.0M/170M [00:02<00:02, 45.2MB/s]
51%|##### | 86.3M/170M [00:02<00:01, 45.6MB/s]
53%|#####3 | 90.7M/170M [00:02<00:02, 41.4MB/s]
57%|#####6 | 96.0M/170M [00:02<00:02, 38.3MB/
s]
60%|###### | 102M/170M [00:02<00:01, 39.6MB/s]
62%|######2 | 106M/170M [00:02<00:01, 37.2MB/s]
66%|######5 | 112M/170M [00:03<00:01, 36.8MB/s]
71%|####### | 120M/170M [00:03<00:01, 38.3MB/s]
75%|#######5 | 128M/170M [00:03<00:01, 41.6MB/s]
80%|######## | 136M/170M [00:03<00:00, 37.6MB/s]
85%|########4 | 144M/170M [00:03<00:00, 42.4MB/s]
88%|########8 | 150M/170M [00:03<00:00, 42.0MB/s]
91%|######### | 154M/170M [00:04<00:00, 41.5MB/s]
94%|#########4| 160M/170M [00:04<00:00, 41.2MB/s]
98%|#########7| 166M/170M [00:04<00:00, 42.3MB/s]
100%|##########| 170M/170M [00:04<00:00, 39.8MB/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 28.645 seconds)
+ **Total running time of the script:** ( 3 minutes 51.087 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 f3adb848a2..3d0e6d691f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -227,7 +227,7 @@ training. Other models require a full post training calibration.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MobileNet_V2_Weights.IMAGENET1K_V1`. You can also use `weights=MobileNet_V2_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 48.0MB/s]
93%|#########2| 12.6M/13.6M [00:00<00:00, 47.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 50.3MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 75.6MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 80.6MB/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)
- 87.9646 87.8905 90.1300 87.6707 0.2985
+ 90.8449 90.7368 94.5931 90.4194 0.5807
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.760 seconds)
+ **Total running time of the script:** ( 1 minutes 21.510 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 360ceab6ed..b15f80838a 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)
- 117.2412 117.3870 119.4369 115.0188 1.0573
+ 120.9982 120.5474 153.8192 119.5517 3.3442
@@ -460,7 +460,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 35.548 seconds)
+ **Total running time of the script:** ( 2 minutes 39.539 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 364f22733d..623b5f0256 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 49.527 seconds)
+ **Total running time of the script:** ( 2 minutes 7.367 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 07cb840af8..c683ba2673 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]
5%|4 | 6468/132723 [00:00<00:01, 64671.43KB/s]
11%|# | 14523/132723 [00:00<00:01, 74003.20KB/s]
17%|#6 | 21924/132723 [00:00<00:01, 68208.73KB/s]
23%|##2 | 29968/132723 [00:00<00:01, 72799.27KB/s]
29%|##8 | 37946/132723 [00:00<00:01, 75229.80KB/s]
35%|###4 | 45957/132723 [00:00<00:01, 76847.84KB/s]
41%|#### | 53949/132723 [00:00<00:01, 77835.91KB/s]
47%|####6 | 61970/132723 [00:00<00:00, 78559.77KB/s]
53%|#####2 | 69843/132723 [00:01<00:01, 56117.19KB/s]
59%|#####8 | 77696/132723 [00:01<00:00, 61498.47KB/s]
64%|######3 | 84603/132723 [00:01<00:00, 61254.61KB/s]
70%|######9 | 92555/132723 [00:01<00:00, 66016.02KB/s]
75%|#######5 | 99600/132723 [00:01<00:00, 56541.97KB/s]
81%|######## | 107491/132723 [00:01<00:00, 62041.22KB/s]
86%|########6 | 114680/132723 [00:01<00:00, 52938.02KB/s]
91%|#########
| 120526/132723 [00:01<00:00, 49061.84KB/s]
97%|#########6| 128361/132723 [00:02<00:00, 55846.31KB/s]
100%|##########| 132723/132723 [00:02<00:00, 62717.12KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 7074/132723 [00:00<00:01, 70718.82KB/s]
11%|#1 | 15152/132723 [00:00<00:01, 59955.16KB/s]
16%|#6 | 21290/132723 [00:00<00:02, 52803.86KB/s]
22%|##2 | 29711/132723 [00:00<00:01, 63189.52KB/s]
27%|##7 | 36293/132723 [00:00<00:01, 51505.17KB/s]
34%|###3 | 44680/132723 [00:00<00:01, 60220.85KB/s]
39%|###9 | 52245/132723 [00:00<00:01, 64507.77KB/s]
46%|####5 | 60675/132723 [00:00<00:01, 70130.45KB/s]
52%|#####2 | 69060/132723 [00:01<00:00, 74088.74KB/s]
58%|#####8 | 77430/132723 [00:01<00:00, 76894.15KB/s]
64%|######4 | 85324/132723 [00:01<00:00, 68011.74KB/s]
71%|####### | 93693/132723 [00:01<00:00, 72235.86KB/s]
76%|#######6 | 101191/132723 [00:01<00:00, 51077.37KB/s]
83%|########2 | 109536/132723 [00:01<00:00, 58116.86KB/s]
88%|########7 | 116328/132723 [00:01<00:00, 52783.27KB/s]
94%|########
#3| 124668/132723 [00:02<00:00, 59769.98KB/s]
100%|##########| 132723/132723 [00:02<00:00, 62573.55KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 3.000 seconds)
+ **Total running time of the script:** ( 4 minutes 10.126 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 9b3b9d6f74..77650bd4ed 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
=================
-**16:43.012** total execution time for **how_to_deploy_models** files:
+**17:48.372** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 04:03.000 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 04:10.126 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:28.645 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:51.087 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:35.548 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:39.539 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:49.527 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 02:07.367 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:16.760 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:21.510 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.460 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:56.628 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:53.915 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:54.138 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:43.004 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:47.615 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:28.792 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:30.534 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:28.355 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:29.823 | 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 534341e1e1..00b0124fa7 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.zipc7319429-031b-4429-996e-d4d371792dae from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip03cbc4e5-669d-4717-a946-baf098d40e36 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 a9a488b965..ec102518c6 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
=================
-**00:55.623** total execution time for **how_to_extend_tvm** files:
+**00:57.290** 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``) | 00:51.751 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:53.336 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.787 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.836 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.077 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.110 | 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 504993420e..226d28322e 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: 23018us [23018us] (48.77%; 48.77%)
- FoldScaleAxis: 24176us [6us] (51.23%; 51.23%)
- FoldConstant: 24170us [1694us] (51.21%; 99.98%)
- InferType: 22476us [22476us] (47.62%; 92.99%)
+ InferType: 23317us [23317us] (48.46%; 48.46%)
+ FoldScaleAxis: 24803us [10us] (51.54%; 51.54%)
+ FoldConstant: 24793us [1726us] (51.52%; 99.96%)
+ InferType: 23066us [23066us] (47.94%; 93.04%)
@@ -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: 22780us [22780us] (48.42%; 48.42%)
- FoldScaleAxis: 24269us [5us] (51.58%; 51.58%)
- FoldConstant: 24264us [1667us] (51.57%; 99.98%)
- InferType: 22597us [22597us] (48.03%; 93.13%)
+ InferType: 22949us [22949us] (48.46%; 48.46%)
+ FoldScaleAxis: 24405us [7us] (51.54%; 51.54%)
+ FoldConstant: 24399us [1751us] (51.52%; 99.97%)
+ InferType: 22647us [22647us] (47.83%; 92.82%)
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 23f7dd7e17..73efd3137f 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: 47.613918 ms
+ Convolution: 40.940990 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 3d5711b3f4..fd0dc486db 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -598,7 +598,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 12.241196 ms
+ conv2d with tensor core: 11.796375 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 12303daa46..26fbc7cd73 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: 0.017968
- Baseline: 3.300610
+ Numpy running time: 0.018450
+ Baseline: 3.284330
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.301371
+ Opt1: 0.316429
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.346604
+ Opt2: 0.353612
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.113008
+ Opt3: 0.115747
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.108601
+ Opt4: 0.109961
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110817
+ Opt5: 0.111417
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.146270
+ Opt6: 0.148707
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 f8af78d02f..2fd894b6a7 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
=================
-**00:34.965** total execution time for **how_to_optimize_operators** files:
+**00:35.826** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.032 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.517 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.836 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:02.058 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.097 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.252 | 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 cbe6573153..0f58cc1102 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**10:30.016** total execution time for **how_to_tune_with_autoscheduler** files:
+**10:29.707** 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``) | 06:30.327 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:23.264 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:45.242 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:47.776 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:12.763 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:14.288 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:33.363 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:35.109 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.472 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.990 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.850 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:14.282 | 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 94f9b3b72c..bdee0a18f1 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 +243,317 @@ 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", 112)
- conv2d_nchw = T.allocate([4], "float32", "local")
- pad_temp_shared = T.allocate([36], "float32", "shared")
- kernel_shared = T.allocate([384], "float32", "shared")
+ blockIdx_x = T.launch_thread("blockIdx.x", 32)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([162], "float32", "shared")
+ kernel_shared = T.allocate([288], "float32", "shared")
threadIdx_x = T.launch_thread("threadIdx.x", 56)
conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(128, 3):
- cse_var_2: T.int32 = rc_outer_outer * 36
- cse_var_1: T.int32 = ry_outer_outer * 3
- pad_temp_shared_1 = T.Buffer((36,), data=pad_temp_shared, scope="shared")
- with T.launch_thread("threadIdx.x", 56) as threadIdx_x_1:
- if T.likely(threadIdx_x_1 < 36):
- data_1 = T.Buffer((25088,), data=data.data)
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[rc_outer_outer * 196 + threadIdx_x_1 // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[13] = T.float32(0)
+ for rc_outer_outer in range(256):
+ cse_var_2: T.int32 = rc_outer_outer * 98
+ cse_var_1: T.int32 = rc_outer_outer * 18
threadIdx_x_1 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((384,), data=kernel_shared, scope="shared")
- kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x // 7 * 147456 + threadIdx_x_1 // 12 * 4608 + cse_var_2 + threadIdx_x_1 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[(threadIdx_x_1 + 56) // 12 * 12 + (threadIdx_x_1 + 8) % 12 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 147456 + (threadIdx_x_1 + 56) // 12 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[(threadIdx_x_1 + 112) // 12 * 12 + (threadIdx_x_1 + 4) % 12 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 147456 + (threadIdx_x_1 + 112) // 12 * 4608 + cse_var_2 + (threadIdx_x_1 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ pad_temp_shared_1 = T.Buffer((162,), data=pad_temp_shared, scope="shared")
+ data_1 = T.Buffer((25088,), data=data.data)
with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 + 168] = kernel_1[blockIdx_x // 7 * 147456 + threadIdx_x_1 // 12 * 4608 + cse_var_2 + threadIdx_x_1 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 64512]
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[(threadIdx_x_1 + 224) // 12 * 12 + (threadIdx_x_1 + 8) % 12 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 147456 + (threadIdx_x_1 + 224) // 12 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(9 <= (threadIdx_x_1 + 56) % 81 and (threadIdx_x_1 + 56) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 81 * 49 + (threadIdx_x_1 + 56) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[(threadIdx_x_1 + 280) // 12 * 12 + (threadIdx_x_1 + 4) % 12 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 147456 + (threadIdx_x_1 + 280) // 12 * 4608 + cse_var_2 + (threadIdx_x_1 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
- with T.launch_thread(threadIdx_x_1, 56):
- if T.likely(threadIdx_x_1 < 48):
- kernel_shared_1[threadIdx_x_1 + 336] = kernel_1[blockIdx_x // 7 * 147456 + threadIdx_x_1 // 12 * 4608 + cse_var_2 + threadIdx_x_1 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 129024]
- for rx_outer_inner in range(3):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 192]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 204]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 195]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 207]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 198]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 18]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 210]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 201]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 21]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 213]
+ if T.likely(threadIdx_x_1 < 50):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(threadIdx_x_1 < 41 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 81 * 49 + (threadIdx_x_1 + 31) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ threadIdx_x_2 = T.env_thread("threadIdx.x")
+ kernel_shared_1 = T.Buffer((288,), data=kernel_shared, scope="shared")
+ kernel_1 = T.Buffer((2359296,), data=kernel.data)
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 56] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 56) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 + 2) % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 112] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 112) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 + 4) % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 168] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 168) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 + 6) % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 224] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ if T.likely(threadIdx_x_2 < 8):
+ kernel_shared_1[threadIdx_x_2 + 280] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 280) // 18 * 4608 + cse_var_1 + threadIdx_x_2 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 9] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 10] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 9] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 10] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 10] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 16] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 10] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 16] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 16] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 17] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 16] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 17] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 18] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 19] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 18] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 19] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 19] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 25] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 19] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 25] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 25] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 26] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 25] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 26] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 81] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 82] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 81] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 82] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 82] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 88] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 82] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 88] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 88] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 89] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 88] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 89] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 90] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 91] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 90] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 91] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 91] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 97] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 91] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 97] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 97] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 98] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 97] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 98] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 99] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 100] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 99] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 100] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 100] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 106] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 100] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 106] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 106] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 107] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 106] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 107] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
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 // 7 * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x // 7 * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_1[blockIdx_x // 7 * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + threadIdx_x % 7 + 784] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x // 7 * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 1] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 2] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 3] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 4] = T.max(conv2d_nchw_1[i1_inner + 8] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 5] = T.max(conv2d_nchw_1[i1_inner + 10] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 6] = T.max(conv2d_nchw_1[i1_inner + 12] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
@@ -350,7 +603,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.356 ms
+ Execution time of this operator: 0.368 ms
@@ -401,34 +654,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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=2)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=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_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_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=7)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=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=2)
+ 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=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_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+ 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=7)
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)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -454,7 +707,7 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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=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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -480,52 +733,300 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define uint64_t unsigned long long
#endif
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[4];
- __shared__ float pad_temp_shared[36];
- __shared__ float kernel_shared[384];
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[162];
+ __shared__ float kernel_shared[288];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 56) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 112) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((((((int)threadIdx.x) + 224) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 280) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 280) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- }
- __syncthreads();
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 204)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 207)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 210)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 213)]));
- }
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 256; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 50) {
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((((int)threadIdx.x) < 41) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 112) / 81) * 49)) + (((((int)threadIdx.x) + 31) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 6) % 18))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 8) % 18))];
+ if (((int)threadIdx.x) < 8) {
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 18) * 4608)) + (rc_outer_outer * 18)) + ((int)threadIdx.x)) + 10)];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -585,7 +1086,7 @@ 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 30.327 seconds)
+ **Total running time of the script:** ( 6 minutes 23.264 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 426c2a7168..0b5b63e9bf 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)
- 8.1389 8.1398 8.1586 8.1184 0.0164
+ 8.1081 8.1105 8.1110 8.1028 0.0037
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 12.763 seconds)
+ **Total running time of the script:** ( 1 minutes 14.288 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 2230e82e9d..e19b0068a4 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)
- 761.2308 754.8867 776.0611 752.7446 10.5230
+ 758.5179 758.6952 758.8663 757.9921 0.3783
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 45.242 seconds)
+ **Total running time of the script:** ( 1 minutes 47.776 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 eb8934b282..51a3879b39 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
@@ -389,85 +389,74 @@ 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(128):
- compute_1 = T.allocate([512], "float32", "global")
- compute_2 = T.Buffer((512,), data=compute_1)
- for i_outer_inner in range(32):
- cse_var_2: T.int32 = i_outer_inner * 16
- cse_var_1: T.int32 = i0_outer_i1_outer_fused % 64 // 2
- compute_2[cse_var_2] = T.float32(0)
- compute_2[cse_var_2 + 1] = T.float32(0)
- compute_2[cse_var_2 + 2] = T.float32(0)
- compute_2[cse_var_2 + 3] = T.float32(0)
- compute_2[cse_var_2 + 4] = T.float32(0)
- compute_2[cse_var_2 + 5] = T.float32(0)
- compute_2[cse_var_2 + 6] = T.float32(0)
- compute_2[cse_var_2 + 7] = T.float32(0)
- compute_2[cse_var_2 + 8] = T.float32(0)
- compute_2[cse_var_2 + 9] = T.float32(0)
- compute_2[cse_var_2 + 10] = T.float32(0)
- compute_2[cse_var_2 + 11] = T.float32(0)
- compute_2[cse_var_2 + 12] = T.float32(0)
- compute_2[cse_var_2 + 13] = T.float32(0)
- compute_2[cse_var_2 + 14] = T.float32(0)
- compute_2[cse_var_2 + 15] = T.float32(0)
- for elem_idx in range(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ 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 nb_j_inner in range(2):
+ for i_inner_init in range(32):
+ cse_var_1: T.int32 = i_inner_init * 32 + nb_j_inner * 16
+ compute_2[cse_var_1] = T.float32(0)
+ compute_2[cse_var_1 + 1] = T.float32(0)
+ compute_2[cse_var_1 + 2] = T.float32(0)
+ compute_2[cse_var_1 + 3] = T.float32(0)
+ compute_2[cse_var_1 + 4] = T.float32(0)
+ compute_2[cse_var_1 + 5] = T.float32(0)
+ compute_2[cse_var_1 + 6] = T.float32(0)
+ compute_2[cse_var_1 + 7] = T.float32(0)
+ compute_2[cse_var_1 + 8] = T.float32(0)
+ compute_2[cse_var_1 + 9] = T.float32(0)
+ compute_2[cse_var_1 + 10] = T.float32(0)
+ compute_2[cse_var_1 + 11] = T.float32(0)
+ compute_2[cse_var_1 + 12] = T.float32(0)
+ 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 % 16 * 2 + nb_j_inner}), 32):
+ cse_var_2 = T.int32()
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_21: T.int32 = elem_idx * 16
+ cse_var_20: T.int32 = i_inner * 32 + nb_j_inner * 16
+ cse_var_19: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_18: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i_inner * 256
+ cse_var_17: T.int32 = cse_var_20 + 9
+ cse_var_16: T.int32 = cse_var_20 + 8
+ cse_var_15: T.int32 = cse_var_20 + 7
+ cse_var_14: T.int32 = cse_var_20 + 6
+ cse_var_13: T.int32 = cse_var_20 + 5
+ cse_var_12: T.int32 = cse_var_20 + 4
+ cse_var_11: T.int32 = cse_var_20 + 3
+ cse_var_10: T.int32 = cse_var_20 + 2
+ cse_var_9: T.int32 = cse_var_20 + 15
+ cse_var_8: T.int32 = cse_var_20 + 14
+ cse_var_7: T.int32 = cse_var_20 + 13
+ cse_var_6: T.int32 = cse_var_20 + 12
+ cse_var_5: T.int32 = cse_var_20 + 11
+ cse_var_4: T.int32 = cse_var_20 + 10
+ cse_var_3: T.int32 = cse_var_20 + 1
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_3: T.int32 = cse_var_2 + 1
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_4: T.int32 = cse_var_2 + 2
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_5: T.int32 = cse_var_2 + 3
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_6: T.int32 = cse_var_2 + 4
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_7: T.int32 = cse_var_2 + 5
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_8: T.int32 = cse_var_2 + 6
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_9: T.int32 = cse_var_2 + 7
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_10: T.int32 = cse_var_2 + 8
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_11: T.int32 = cse_var_2 + 9
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_12: T.int32 = cse_var_2 + 10
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_13: T.int32 = cse_var_2 + 11
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_14: T.int32 = cse_var_2 + 12
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_15: T.int32 = cse_var_2 + 13
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_16: T.int32 = cse_var_2 + 14
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_17: T.int32 = cse_var_2 + 15
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- for i0_inner in range(64):
- cse_var_18: T.int32 = i0_outer_i1_outer_fused // 64 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 64 * 8
+ compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ for i0_inner in range(32):
+ cse_var_22: T.int32 = i0_outer_i1_outer_fused // 16 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_18:cse_var_18 + 8] = T.max(compute_2[i0_inner * 8:i0_inner * 8 + 8] + placeholder_5[cse_var_18:cse_var_18 + 8], T.Broadcast(T.float32(0), 8))
+ compute_3[cse_var_22:cse_var_22 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_22:cse_var_22 + 32], T.Broadcast(T.float32(0), 32))
@@ -517,7 +506,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.027 ms
+ Execution time of this operator: 1.757 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 296f8962b7..9c7e09d175 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:36.689** total execution time for **how_to_tune_with_autotvm** files:
+**00:43.897** 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``) | 00:36.651 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.859 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.005 | 0.0 MB |
++--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 1065929989..1c5c68598d 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
@@ -268,7 +268,8 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 272.34/272.34 result: MeasureResult(costs=(0.0008500458167938932,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.174592971801758, timestamp=1683225095.3057506) [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4743550
+ No: 2 GFLOPS: 0.00/272.34 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
@@ -390,8 +391,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10211556
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8385369
+ No: 3 GFLOPS: 0.00/272.34 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
@@ -513,8 +514,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10129203
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6136379
+ No: 4 GFLOPS: 0.00/272.34 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
@@ -636,8 +637,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,338839
- No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8045517
+ No: 5 GFLOPS: 0.00/272.34 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
@@ -759,8 +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, 1, 8, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,764709
- No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,228621
+ No: 6 GFLOPS: 32.79/272.34 result: MeasureResult(costs=(0.0070609998125000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.427013874053955, timestamp=1683225100.0333686) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5479815
+ No: 7 GFLOPS: 0.00/272.34 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
@@ -882,8 +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, 1, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5775929
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8702588
+ No: 8 GFLOPS: 0.00/272.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1005,9 +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, 4, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9385274
- No: 7 GFLOPS: 3.37/3.37 result: MeasureResult(costs=(0.0686225355,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6284170150756836, timestamp=1683156679.621043) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2060301
- No: 8 GFLOPS: 0.00/3.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4121321
+ No: 9 GFLOPS: 0.00/272.34 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
@@ -1129,8 +1130,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4859951
- No: 9 GFLOPS: 0.00/3.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2950561
+ No: 10 GFLOPS: 62.15/272.34 result: MeasureResult(costs=(0.0037250195172413795,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.0271501541137695, timestamp=1683225105.8088949) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8432382
+ No: 11 GFLOPS: 430.70/430.70 result: MeasureResult(costs=(0.0005375034894736843,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8615736961364746, timestamp=1683225106.6741772) [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8422930
+ No: 12 GFLOPS: 0.00/430.70 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
@@ -1252,11 +1255,8 @@ 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, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3993134
- No: 10 GFLOPS: 35.36/35.36 result: MeasureResult(costs=(0.006547736125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4530391693115234, timestamp=1683156681.5583606) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3314876
- No: 11 GFLOPS: 37.19/37.19 result: MeasureResult(costs=(0.006225197235294118,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.674783706665039, timestamp=1683156682.4533904) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6241895
- No: 12 GFLOPS: 394.35/394.35 result: MeasureResult(costs=(0.0005870448771929825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.687148094177246, timestamp=1683156683.2791271) [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3219490
- No: 13 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2574137
+ No: 13 GFLOPS: 0.00/430.70 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
@@ -1378,10 +1378,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9321397
- No: 14 GFLOPS: 51.22/394.35 result: MeasureResult(costs=(0.00451943052,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.4141457080841064, timestamp=1683156687.917114) [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8178190
- No: 15 GFLOPS: 6.69/394.35 result: MeasureResult(costs=(0.0346064795,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.387319326400757, timestamp=1683156688.9063199) [('tile_f', [-1, 64, 1, 1]), ('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, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,985166
- No: 16 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5128458
+ No: 14 GFLOPS: 0.00/430.70 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
@@ -1503,8 +1501,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6309053
- No: 17 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,772493
+ No: 15 GFLOPS: 0.00/430.70 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
@@ -1626,8 +1624,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5791806
- No: 18 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8396788
+ No: 16 GFLOPS: 0.00/430.70 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
@@ -1749,8 +1747,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2960797
- No: 19 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3371207
+ No: 17 GFLOPS: 0.00/430.70 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
@@ -1872,8 +1870,271 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10189207
- No: 20 GFLOPS: 222.31/394.35 result: MeasureResult(costs=(0.0010413349607843137,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.628429651260376, timestamp=1683156690.7553368) [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9490452
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1213036
+ No: 18 GFLOPS: 0.00/430.70 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:401
+ 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:387
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:282
+ 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:401
+ 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:387
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:282
+ 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, 8, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9860112
+ No: 19 GFLOPS: 0.00/430.70 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3580729
+ No: 20 GFLOPS: 0.00/430.70 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:401
+ 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:387
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:282
+ 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:401
+ 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:387
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:282
+ 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, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3014641
@@ -1928,9 +2189,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3219490
+ [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8422930
Finish loading 20 records
- Time cost of this operator: 0.000969
+ Time cost of this operator: 0.000944
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 14665836d9..57e82db2d3 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 311.5 98.716 (1, 2, 10, 10, 3) 2 1 [311.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.13 0.992 (1, 6, 10, 10) 1 1 [3.13]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.292 (1, 1, 10, 10, 3) 1 1 [0.923]
- Total_time - 315.553 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.5 98.732 (1, 2, 10, 10, 3) 2 1 [315.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.092 0.968 (1, 6, 10, 10) 1 1 [3.092]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.958 0.3 (1, 1, 10, 10, 3) 1 1 [0.958]
+ Total_time - 319.551 - - - - -
@@ -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 137.4 98.115 (1, 6, 10, 10, 1) 2 1 [137.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.72 1.228 (1, 6, 10, 10) 1 1 [1.72]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.92 0.657 (1, 1, 10, 10, 3) 1 1 [0.92]
- Total_time - 140.04 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 184.5 98.341 (1, 1, 10, 10, 6) 2 1 [184.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.115 1.127 (1, 6, 10, 10) 1 1 [2.115]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.998 0.532 (1, 3, 10, 10, 1) 1 1 [0.998]
+ Total_time - 187.613 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.737 seconds)
+ **Total running time of the script:** ( 1 minutes 27.707 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 f367bcd5b9..c074bf0c19 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_pytorch.rst.txt
@@ -118,7 +118,7 @@ download a cat image and preprocess it to use as the model input.
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/ao/quantization/utils.py:281: UserWarning: must run observer before calling calculate_qparams. Returning default values.
"must run observer before calling calculate_qparams. " +
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
-
0%| | 0.00/3.42M [00:00<?, ?B/s]
61%|######1 | 2.09M/3.42M [00:00<00:00, 21.9MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 33.8MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 82.9MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.089 seconds)
+ **Total running time of the script:** ( 1 minutes 22.334 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 b1020330fd..8701b52df2 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/tmpt420wpnj/images/random'
+ '/tmp/tmpo7e4iq76/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [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/tmpt420wpnj/images/target contains 8144 images
- /tmp/tmpt420wpnj/images/random contains 5000 images
+ /tmp/tmpo7e4iq76/images/target contains 8144 images
+ /tmp/tmpo7e4iq76/images/random contains 5000 images
@@ -493,13 +493,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 40s - loss: 0.2036 - accuracy: 0.9255 - val_loss: 0.1181 - val_accuracy: 0.9630 - 40s/epoch - 123ms/step
+ 328/328 - 41s - loss: 0.2368 - accuracy: 0.9198 - val_loss: 0.1113 - val_accuracy: 0.9626 - 41s/epoch - 124ms/step
Epoch 2/3
- 328/328 - 35s - loss: 0.1003 - accuracy: 0.9627 - val_loss: 0.1036 - val_accuracy: 0.9637 - 35s/epoch - 106ms/step
+ 328/328 - 35s - loss: 0.1048 - accuracy: 0.9607 - val_loss: 0.1822 - val_accuracy: 0.9335 - 35s/epoch - 108ms/step
Epoch 3/3
- 328/328 - 35s - loss: 0.0637 - accuracy: 0.9747 - val_loss: 0.1087 - val_accuracy: 0.9671 - 35s/epoch - 106ms/step
+ 328/328 - 35s - loss: 0.0770 - accuracy: 0.9711 - val_loss: 0.0892 - val_accuracy: 0.9668 - 35s/epoch - 108ms/step
- <keras.callbacks.History object at 0x7f03b740a750>
+ <keras.callbacks.History object at 0x7f01b5353d90>
@@ -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 22.337 seconds)
+ **Total running time of the script:** ( 4 minutes 30.507 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 b90688764a..d4d6ed5829 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
@@ -5,24 +5,24 @@
Computation times
=================
-**07:30.155** total execution time for **how_to_work_with_microtvm** files:
+**07:47.365** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:22.337 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:30.507 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:22.737 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:27.707 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:19.089 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:22.334 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.632 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.849 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:08.031 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:08.277 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.329 | 0.0 MB |
-+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.691 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``) | 00:00.000 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
++-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_mlperftiny.py` (``micro_mlperftiny.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 b30594624f..cac30909b0 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
=================
-**00:36.968** total execution time for **how_to_work_with_relay** files:
+**00:38.044** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.258 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.322 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:02.908 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:03.017 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.796 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.698 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index ebac8002d1..ecbf27af4c 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 0x7effece51950>
+ <function my_cuda_math_rule at 0x7efe0c5473b0>
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 b4841cfc4c..8fff1b98ae 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:09.169** total execution time for **how_to_work_with_schedules** files:
+**00:05.458** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.390 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.687 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.283 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.244 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.615 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.628 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.596 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.614 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.133 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.134 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.065 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.064 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.057 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.058 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.030 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 8bef04d0a3..a62e6984cd 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
=================
-**00:32.062** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:32.917** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:32.054 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:32.910 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 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 f84af6a6da..daca44e278 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -293,7 +293,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 33.81s!
+ resnet18_v1 inference graph built in 35.11s!
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 122ff632ad..c7efa87a44 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 23.21s!
+ yolov3-tiny inference graph built in 24.18s!
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 adf3cf46c0..2dfb59e209 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:40.968** total execution time for **topic_vta_tutorials_frontend** files:
+**01:43.425** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.663 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:52.014 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.305 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.411 | 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 a44899e9e9..704b7319d6 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
=================
-**00:03.256** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.314** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.773 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.807 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.483 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.507 | 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 ce3823c880..d5308d1281 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
=================
-**00:00.809** total execution time for **topic_vta_tutorials** files:
+**00:00.862** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.417 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.443 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.393 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.419 | 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 b501372a3b..094b87e2ce 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -318,7 +318,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 92.490 ms
+ Execution time of this operator: 94.221 ms
@@ -434,7 +434,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.151 seconds)
+ **Total running time of the script:** ( 1 minutes 31.405 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 a95d1abcf1..921f1af628 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: 0.51/0.51 result: MeasureResult(costs=(0.5237239936,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.622305393218994, timestamp=1683154987.1998823) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
- No: 2 GFLOPS: 11.94/11.94 result: MeasureResult(costs=(0.02249086,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6137738227844238, timestamp=1683154987.8225126) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
- No: 3 GFLOPS: 13.57/13.57 result: MeasureResult(costs=(0.0197760538,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6246299743652344, timestamp=1683154989.6560426) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
- No: 4 GFLOPS: 0.52/13.57 result: MeasureResult(costs=(0.5169321668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.494956970214844, timestamp=1683154999.4288502) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
- No: 5 GFLOPS: 1.58/13.57 result: MeasureResult(costs=(0.1695864266,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9545950889587402, timestamp=1683155002.5158095) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
- No: 6 GFLOPS: 1.53/13.57 result: MeasureResult(costs=(0.1753377892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0516767501831055, timestamp=1683155006.8181026) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
- No: 7 GFLOPS: 3.29/13.57 result: MeasureResult(costs=(0.0815368112,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5529429912567139, timestamp=1683155008.3744652) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 8 GFLOPS: 0.88/13.57 result: MeasureResult(costs=(0.30414283000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.098167657852173, timestamp=1683155013.4912431) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 9 GFLOPS: 10.57/13.57 result: MeasureResult(costs=(0.025396922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.609248161315918, timestamp=1683155014.248298) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
- No: 10 GFLOPS: 14.06/14.06 result: MeasureResult(costs=(0.0190886888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5325667858123779, timestamp=1683155014.8051574) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+ No: 1 GFLOPS: 11.61/11.61 result: MeasureResult(costs=(0.0231162082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6543011665344238, timestamp=1683223347.3968215) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+ No: 2 GFLOPS: 2.61/11.61 result: MeasureResult(costs=(0.10265298479999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.888545274734497, timestamp=1683223349.29835) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
+ No: 3 GFLOPS: 4.38/11.61 result: MeasureResult(costs=(0.06124216280000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.254276990890503, timestamp=1683223351.8523116) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
+ No: 4 GFLOPS: 0.50/11.61 result: MeasureResult(costs=(0.5349444489999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.807214260101318, timestamp=1683223361.9789934) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+ No: 5 GFLOPS: 1.39/11.61 result: MeasureResult(costs=(0.19252363960000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.309635639190674, timestamp=1683223365.7692535) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
+ No: 6 GFLOPS: 11.57/11.61 result: MeasureResult(costs=(0.023198192200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6228973865509033, timestamp=1683223366.4096155) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+ No: 7 GFLOPS: 8.96/11.61 result: MeasureResult(costs=(0.029950314999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.0795331001281738, timestamp=1683223368.450017) [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
+ No: 8 GFLOPS: 11.62/11.62 result: MeasureResult(costs=(0.0230984046,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6422500610351562, timestamp=1683223369.0853057) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
+ No: 9 GFLOPS: 11.49/11.62 result: MeasureResult(costs=(0.0233708374,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.60260009765625, timestamp=1683223369.8020158) [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
+ No: 10 GFLOPS: 11.66/11.66 result: MeasureResult(costs=(0.0230168966,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.59712815284729, timestamp=1683223370.4319348) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index deacdc8125..3ab77c7d8e 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': 516.0434589399995, 'median': 516.7266176999988, 'std': 1.4996019181741262}
+ {'mean': 513.4662605699486, 'median': 513.2093307500327, 'std': 2.184630412673929}
@@ -582,31 +582,29 @@ 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: 23.66/ 23.66 GFLOPS | Progress: (4/20) | 10.10 s
[Task 1/25] Current/Best: 15.03/ 23.66 GFLOPS | Progress: (8/20) | 15.25 s
[Task 1/25] Current/Best: 7.55/ 23.66 GFLOPS | Progress: (12/20) | 18.41 s
[Task 1/25] Current/Best: 9.44/ 23.66 GFLOPS | Progress: (16/20) | 20.63 s
[Task 1/25] Current/Best: 14.89/ 23.66 GFLOPS | Progress: (20/20) | 27.44 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 15.85/ 19.97 GFLOPS | Progress: (4/20) | 4.53 s
[Task 2/25] Current/Best: 7.86/ 19.97 GFLOPS | Progress: (8/20) | 6.78 s
[Task 2/25] Current/Best: 13.32/ 21.26 GFLOPS | Progress: (12/20) | 8.67 s
[Task 2/25] Current/Best: 13.22/ 21.26 GFLOPS | Progress: (16/20) | 10.62 s
[Task 2/25] Current/Best: 13.37/ 21.26 GFLOPS | Progress: (20/20) | 12.55 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 5.58/ 17.06 GFLOPS | Progress: (4/20) | 5.61 s
[Task 3/25] Current/Best: 16.94/ 17.06 GFLOPS | Progress: (8/20) | 8.26 s
[Task 3/25] Current/Best: 11.57/ 19.07 GFLOPS | Progress: (12/20) | 10.31 s
[Task 3/25] Current/Best: 14.92/ 22.81 GFLOPS | Progress: (16/20) | 12.56 s
[Task 3/25] Current/Best: 9.24/ 23.02 GFLOPS | Progress: (20/20) | 14.88 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 6.67/ 20.16 GFLOPS | Progress: (4/20) | 5.09 s
[Task 4/25] Current/Best: 16.29/ 20.16 GFLOPS | Progress: (8/20) | 7.29 s
[Task 4/25] Current/Best: 16.81/ 20.16 GFLOPS | Progress: (12/20) | 11.28 s
[Task 4/25] Current/Best: 9.52/ 20.16 GFLOPS | Progress: (16/20) | 17.87 s
[Task 4/25] Current/Best: 7.14/ 20.16 GFLOPS | Progress: (20/20) | 20.10 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 17.74/ 17.74 GFLOPS | Progress: (4/20) | 5.22 s
[Task 5/25] Current/Best: 10.56/ 20.50 GFLOPS | Progress: (8/20) | 7.42 s
[Task 5/25] Current/Best: 17.52/ 20.50 GFLOPS | Progress: (12/20) | 9.41 s
[Task 5/25] Current/Best: 14.26/ 20.50 GFLOPS | Progress: (16/20) | 11.48 s
[Task 5/25] Current/Best: 17.57/ 20.50 GFLOPS | Progress: (20/20) | 13.59 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 8.23/ 17.84 GFLOPS | Progress: (4/20) | 5.13 s
[Task 6/25] Current/Best: 8.59/ 17.84 GFLOPS | Progress: (8/20) | 10.58 s
[Task 6/25] Current/Best: 4.96/ 18.11 GFLOPS | Progress: (12/20) | 13.06 s
[Task 6/25] Current/Best: 13.01/ 20.24 GFLOPS | Progress: (16/20) | 16.54 s
[Task 6/25] Current/Best: 2.84/ 20.24 GFLOPS | Progress: (20/20) | 21.60 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 14.86/ 17.42 GFLOPS | Progress: (4/20) | 5.42 s
[Task 7/25] Current/Best: 22.81/ 22.81 GFLOPS | Progress: (8/20) | 7.67 s
[Task 7/25] Current/Best: 15.96/ 22.81 GFLOPS | Progress: (12/20) | 9.75 s
[Task 7/25] Current/Best: 18.03/ 22.81 GFLOPS | Progress: (16/20) | 12.53 s
[Task 7/25] Current/Best: 13.44/ 22.81 GFLOPS | Progress: (20/20) | 16.51 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 2.76/ 19.54 GFLOPS | Progress: (4/20) | 5.68 s
[Task 8/25] Current/Best: 6.03/ 19.54 GFLOPS | Progress: (8/20) | 15.19 s
[Task 8/25] Current/Best: 13.90/ 19.54 GFLOPS | Progress: (12/20) | 20.26 s
[Task 8/25] Current/Best: 4.94/ 19.54 GFLOPS | Progress: (16/20) | 31.99 s
[Task 8/25] Current/Best: 9.99/ 19.54 GFLOPS | Progress: (20/20) | 35.50 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 13.78/ 20.35 GFLOPS | Progress: (4/20) | 4.38 s
[Task 9/25] Current/Best: 9.12/ 20.35 GFLOPS | Progress: (8/20) | 8.29 s
[Task 9/25] Current/Best: 9.94/ 20.35 GFLOPS | Progress: (12/20) | 11.79 s
[Task 9/25] Current/Best: 8.20/ 21.34 GFLOPS | Progress: (16/20) | 13.82 s
[Task 9/25] Current/Best: 20.23/ 21.34 GFLOPS | Progress: (20/2
0) | 15.55 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 14.74/ 16.11 GFLOPS | Progress: (4/20) | 4.81 s
[Task 10/25] Current/Best: 6.98/ 16.11 GFLOPS | Progress: (8/20) | 8.33 s
[Task 10/25] Current/Best: 5.36/ 16.11 GFLOPS | Progress: (12/20) | 10.91 s
[Task 10/25] Current/Best: 16.51/ 16.51 GFLOPS | Progress: (16/20) | 12.68 s
[Task 10/25] Current/Best: 21.93/ 21.93 GFLOPS | Progress: (20/20) | 16.12 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 6.23/ 15.92 GFLOPS | Progress: (4/20) | 6.63 s
[Task 11/25] Current/Best: 15.03/ 15.92 GFLOPS | Progress: (8/20) | 10.02 s
[Task 11/25] Current/Best: 6.15/ 20.41 GFLOPS | Progress: (12/20) | 12.68 s
[Task 11/25] Current/Best: 18.68/ 21.84 GFLOPS | Progress: (16/20) | 15.43 s
[Task 11/25] Current/Best: 11.94/ 21.84 GFLOPS | Progress: (20/20) | 18.23 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 10.03/ 14.72 GFLOPS | Progress: (4/20) | 5.41 s
[Task 12/25] Current/Best: 13.90/ 15.52 GFLOPS | Progress: (8/20) | 9.06 s
[Task 12/25] Current/Best: 2.51/ 16.46 GFLOPS | Progress: (12/20) | 12.00 s
[Task 12/25] Current/Best: 11.26/ 16.46 GFLOPS | Progress: (16/20) | 15.55 s
[Task 12/25] Current/Best: 5.93/ 17.46 GFLOPS | Progress: (20/20) | 18.02 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 10.37/ 18.55 GFLOPS | Progress: (4/20) | 5.50 s
[Task 13/25] Current/Best: 9.45/ 18.55 GFLOPS | Progress: (8/20) | 8.44 s
[Task 13/25] Current/Best: 12.86/ 22.27 GFLOPS | Progress: (12/20) | 11.22 s
[Task 13/25] Current/Best: 9.08/ 22.27 GFLOPS | Progress: (16/20) | 14.80 s
[Task 13/25] Current/Best: 20.75/ 22.27 GFLOPS | Progress: (20/20) | 17.46 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 18.49/ 18.49 GFLOPS | Progress: (4/20) | 6.86 s
[Task 14/25] Current/Best: 4.74/ 18.49 GFLOPS | Progress: (8/20) | 9.27 s
[Task 14/25] Current/Best: 12.13/ 18.49 GFLOPS | Progress: (12/20) | 12.74 s
[Task 14/25] Current/Best: 10.95/ 18.82 GFLOPS | Progress: (16/20) | 16.55 s
[Task 14/25] Current/Best: 13.36/ 18.82 GFLOPS | Progress: (20/20) | 20.89 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 15/25] Current/Best: 6.18/ 18.22 GFLOPS | Progress: (4/20) | 5.67 s
[Task 15/25] Current/Best: 21.08/ 21.37 GFLOPS | Progress: (8/20) | 8.13 s
[Task 15/25] Current/Best: 18.90/ 21.37 GFLOPS | Progress: (12/20) | 11.46 s
[Task 15/25] Current/Best: 12.46/ 21.37 GFLOPS | Progress: (16/20) | 14.51 s
[Task 15/25] Current/Best: 16.33/ 21.37 GFLOPS | Progress: (20/20) | 18.91 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 12.66/ 14.75 GFLOPS | Progress: (4/20) | 6.21 s
[Task 16/25] Current/Best: 13.81/ 22.75 GFLOPS | Progress: (8/20) | 8.61 s
[Task 16/25] Current/Best: 18.15/ 22.75 GFLOPS | Progress: (12/20) | 12.17 s
[Task 16/25] Current/Best: 6.92/ 22.75 GFLOPS | Progress: (16/20) | 15.89 s
[Task 16/25] Current/Best: 6.99/ 22.75 GFLOPS | Progress: (20/20) | 18.97 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 19.51/ 19.51 GFLOPS | Progress: (4/20) | 5.00 s
[Task 17/25] Current/Best: 12.22/ 22.40 GFLOPS | Progress: (8/20) | 7.95 s
[Task 17/25] Current/Best: 6.26/ 22.40 GFLOPS | Progress: (12/20) | 10.59 s
[Task 17/25] Current/Best: 13.73/ 22.40 GFLOPS | Progress: (16/20) | 13.71 s
[Task 17/25] Current/Best: 6.22/ 22.40 GFLOPS | Progress: (20/20) | 16.16 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/20) | 4.73 s
[Task 18/25] Current/Best: 11.80/ 18.14 GFLOPS | Progress: (8/20) | 12.51 s
[Task 18/25] Current/Best: 6.06/ 18.14 GFLOPS | Progress: (12/20) | 15.25 s
[Task 18/25] Current/Best: 17.06/ 23.20 GFLOPS | Progress: (16/20) | 18.94 s
[Task 18/25] Current/Best: 12.07/ 23.20 GFLOPS | Progress: (20/20) | 22.10 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 10.11/ 20.28 GFLOPS | Progress: (4/20) | 6.17 s
[Task 19/25] Current/Best: 18.42/ 20.28 GFLOPS | Progress: (8/20) | 8.92 s
[Task 19/25] Current/Best: 19.55/ 20.70 GFLOPS | Progress: (12/20) | 12.48 s
[Task 19/25] Current/Best: 9.75/ 21.38 GFLOPS | Progress: (16/20) | 15.90 s
[Task 19/25] Current/Best: 12.38/ 21.38 GFLOPS | Progress: (20/20) | 18.18 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 12.82/ 12.82 GFLOPS | Progress: (4/20) | 5.78 s
[Task 20/25] Current/Best: 18.11/ 18.11 GFLOPS | Progress: (8/20) | 7.63 s
[Task 20/25] Current/Best: 14.58/ 18.11 GFLOPS | Progress: (12/20) | 11.14 s
[Task 20/25] Current/Best: 13.30/ 18.11 GFLOPS | Progress: (16/20) | 13.51 s
[Task 20/25] Current/Best: 17.06/ 18.11 GFLOPS | Progress: (20/20) | 16.95 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 21/25] Current/Best: 5.41/ 18.29 GFLOPS | Progress: (4/20) | 6.23 s
[Task 21/25] Current/Best: 8.87/ 18.29 GFLOPS | Progress: (8/20) | 8.73 s
[Task 21/25] Current/Best: 4.49/ 22.96 GFLOPS | Progress: (12/20) | 11.86 s
[Task 21/25] Current/Best: 23.09/ 23.09 GFLOPS | Progress: (16/20) | 13.51 s
[Task 21/25] Current/Best: 8.87/ 23.09 GFLOPS | Progress: (20/20) | 15.19 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 10.85/ 18.96 GFLOPS | Progress: (4/20) | 5.94 s
[Task 22/25] Current/Best: 5.06/ 18.96 GFLOPS | Progress: (8/20) | 8.65 s
[Task 22/25] Current/Best: 10.36/ 18.96 GFLOPS | Progress: (12/20) | 12.47 s
[Task 22/25] Current/Best: 4.22/ 18.99 GFLOPS | Progress: (16/20) | 15.23 s
[Task 22/25] Current/Best: 15.64/ 18.99 GFLOPS | Progress: (20/20) | 17.19 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 2.72/ 12.40 GFLOPS | Progress: (4/20) | 6.27 s
[Task 23/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (8/20) | 11.98 s
[Task 23/25] Current/Best: 22.48/ 22.48 GFLOPS | Progress: (12/20) | 14.56 s
[Task 23/25] Current/Best: 22.35/ 22.58 GFLOPS | Progress: (16/20) | 19.23 s
[Task 23/25] Current/Best: 6.04/ 22.58 GFLOPS | Progress: (20/20) | 23.17 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 4.06/ 7.23 GFLOPS | Progress: (4/20) | 5.71 s
[Task 24/25] Current/Best: 6.04/ 10.69 GFLOPS | Progress: (8/20) | 16.35 s
[Task 24/25] Current/Best: 7.85/ 10.69 GFLOPS | Progress: (12/20) | 19.28 s
[Task 24/25] Current/Best: 2.45/ 10.69 GFLOPS | Progress: (16/20) | 29.94 s
[Task 24/25] Current/Best: 4.19/ 10.69 GFLOPS | Progress: (20/20) | 33.36 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 25/25] Current/Best: 3.04/ 9.83 GFLOPS | Progress: (4/20) | 4.39 s
[Task 25/25] Current/Best: 6.18/ 9.83 GFLOPS | Progress: (8/20) | 15.30 s
[Task 25/25] Current/Best: 5.23/ 9.83 GFLOPS | Progress: (12/20) | 18.51 s
[Task 25/25] Current/Best: 3.09/ 9.83 GFLOPS | Progress: (16/20) | 20.21 s
[Task 25/25] Current/Best: 6.31/ 9.83 GFLOPS | Progress: (20/20) | 21.93 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (4/20) | 10.96 s
[Task 1/25] Current/Best: 23.77/ 23.77 GFLOPS | Progress: (8/20) | 16.35 s
[Task 1/25] Current/Best: 12.56/ 23.77 GFLOPS | Progress: (12/20) | 20.03 s
[Task 1/25] Current/Best: 11.70/ 23.77 GFLOPS | Progress: (16/20) | 22.37 s
[Task 1/25] Current/Best: 23.79/ 23.79 GFLOPS | Progress: (20/20) | 25.61 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 19.71/ 19.71 GFLOPS | Progress: (4/20) | 4.23 s
[Task 2/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (8/20) | 5.67 s
[Task 2/25] Current/Best: 18.64/ 19.99 GFLOPS | Progress: (12/20) | 7.37 s
[Task 2/25] Current/Best: 11.91/ 19.99 GFLOPS | Progress: (16/20) | 9.30 s
[Task 2/25] Current/Best: 16.25/ 19.99 GFLOPS | Progress: (20/20) | 11.39 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 11.24/ 16.20 GFLOPS | Progress: (4/20) | 5.51 s
[Task 3/25] Current/Best: 9.25/ 16.20 GFLOPS | Progress: (8/20) | 7.90 s
[Task 3/25] Current/Best: 6.16/ 16.20 GFLOPS | Progress: (12/20) | 10.50 s
[Task 3/25] Current/Best: 6.20/ 16.20 GFLOPS | Progress: (16/20) | 13.04 s
[Task 3/25] Current/Best: 5.88/ 20.98 GFLOPS | Progress: (20/20) | 15.74 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 11.66/ 16.56 GFLOPS | Progress: (4/20) | 6.30 s
[Task 4/25] Current/Best: 14.76/ 16.56 GFLOPS | Progress: (8/20) | 8.83 s
[Task 4/25] Current/Best: 12.20/ 16.56 GFLOPS | Progress: (12/20) | 14.01 s
[Task 4/25] Current/Best: 13.17/ 16.56 GFLOPS | Progress: (16/20) | 17.22 s
[Task 4/25] Current/Best: 12.73/ 16.56 GFLOPS | Progress: (20/20) | 19.71 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 12.95/ 19.96 GFLOPS | Progress: (4/20) | 4.48 s
[Task 5/25] Current/Best: 4.79/ 21.49 GFLOPS | Progress: (8/20) | 7.09 s
[Task 5/25] Current/Best: 17.69/ 21.49 GFLOPS | Progress: (12/20) | 9.29 s
[Task 5/25] Current/Best: 20.49/ 21.49 GFLOPS | Progress: (16/20) | 11.50 s
[Task 5/25] Current/Best: 2.93/ 21.49 GFLOPS | Progress: (20/20) | 13.85 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 5.73/ 18.60 GFLOPS | Progress: (4/20) | 5.11 s
[Task 6/25] Current/Best: 18.44/ 18.60 GFLOPS | Progress: (8/20) | 7.38 s
[Task 6/25] Current/Best: 5.00/ 18.60 GFLOPS | Progress: (12/20) | 10.47 s
[Task 6/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (16/20) | 13.05 s
[Task 6/25] Current/Best: 13.82/ 23.23 GFLOPS | Progress: (20/20) | 15.45 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 15.34/ 20.00 GFLOPS | Progress: (4/20) | 5.10 s
[Task 7/25] Current/Best: 12.75/ 20.57 GFLOPS | Progress: (8/20) | 7.88 s
[Task 7/25] Current/Best: 15.66/ 20.57 GFLOPS | Progress: (12/20) | 11.79 s
[Task 7/25] Current/Best: 14.02/ 20.57 GFLOPS | Progress: (16/20) | 14.05 s
[Task 7/25] Current/Best: 11.04/ 20.57 GFLOPS | Progress: (20/20) | 17.33 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 14.18/ 14.18 GFLOPS | Progress: (4/20) | 12.62 s
[Task 8/25] Current/Best: 5.31/ 20.60 GFLOPS | Progress: (8/20) | 19.13 s
[Task 8/25] Current/Best: 14.11/ 20.60 GFLOPS | Progress: (12/20) | 26.36 s
[Task 8/25] Current/Best: 5.89/ 20.60 GFLOPS | Progress: (16/20) | 37.21 s
[Task 8/25] Current/Best: 13.04/ 20.60 GFLOPS | Progress: (20/20) | 40.32 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 5.92/ 16.34 GFLOPS | Progress: (4/20) | 4.86 s
[Task 9/25] Current/Best: 11.67/ 16.96 GFLOPS | Progress: (8/20) | 11.29 s
[Task 9/25] Current/Best: 8.14/ 21.90 GFLOPS | Progress: (12/20) | 18.62 s
[Task 9/25] Current/Best: 14.17/ 21.90 GFLOPS | Progress: (16/20) | 24.53 s
[Task 9/25] Current/Best: 13.94/ 23.04 GFLOPS | Progress: (20/20) | 27.52 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 16.59/ 18.26 GFLOPS | Progress: (4/20) | 4.90 s
[Task 10/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (8/20) | 7.36 s
[Task 10/25] Current/Best: 18.63/ 20.56 GFLOPS | Progress: (12/20) | 10.84 s
[Task 10/25] Current/Best: 5.25/ 20.56 GFLOPS | Progress: (16/20) | 12.74 s
[Task 10/25] Current/Best: 12.22/ 20.56 GFLOPS | Progress: (20/20) | 16.44 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 8.00/ 17.59 GFLOPS | Progress: (4/20) | 6.07 s
[Task 11/25] Current/Best: 6.27/ 17.59 GFLOPS | Progress: (8/20) | 9.29 s
[Task 11/25] Current/Best: 13.52/ 17.59 GFLOPS | Progress: (12/20) | 12.25 s
[Task 11/25] Current/Best: 17.84/ 18.37 GFLOPS | Progress: (16/20) | 16.08 s
[Task 11/25] Current/Best: 9.41/ 18.37 GFLOPS | Progress: (20/20) | 18.74 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 8.21/ 17.86 GFLOPS | Progress: (4/20) | 5.29 s
[Task 12/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (8/20) | 7.51 s
[Task 12/25] Current/Best: 4.59/ 21.19 GFLOPS | Progress: (12/20) | 9.82 s
[Task 12/25] Current/Best: 9.66/ 21.19 GFLOPS | Progress: (16/20) | 13.18 s
[Task 12/25] Current/Best: 5.35/ 21.19 GFLOPS | Progress: (20/20) | 15.57 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 3.09/ 11.81 GFLOPS | Progress: (4/20) | 6.98 s
[Task 13/25] Current/Best: 16.15/ 16.15 GFLOPS | Progress: (8/20) | 10.05 s
[Task 13/25] Current/Best: 5.82/ 16.15 GFLOPS | Progress: (12/20) | 15.67 s
[Task 13/25] Current/Best: 11.99/ 16.15 GFLOPS | Progress: (16/20) | 20.31 s
[Task 13/25] Current/Best: 13.23/ 19.65 GFLOPS | Progress: (20/20) | 23.11 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 4.73/ 14.88 GFLOPS | Progress: (4/20) | 5.75 s
[Task 14/25] Current/Best: 7.48/ 16.14 GFLOPS | Progress: (8/20) | 7.85 s
[Task 14/25] Current/Best: 10.75/ 16.14 GFLOPS | Progress: (12/20) | 14.18 s
[Task 14/25] Current/Best: 14.37/ 16.14 GFLOPS | Progress: (16/20) | 16.05 s
[Task 14/25] Current/Best: 12.96/ 16.14 GFLOPS | Progress: (20/20) | 24.31 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 10.30/ 10.30 GFLOPS | Progress: (4/20) | 5.98 s Done.
+
[Task 15/25] Current/Best: 3.15/ 15.67 GFLOPS | Progress: (8/20) | 9.64 s
[Task 15/25] Current/Best: 19.62/ 19.62 GFLOPS | Progress: (12/20) | 11.25 s
[Task 15/25] Current/Best: 19.84/ 21.13 GFLOPS | Progress: (16/20) | 16.03 s
[Task 15/25] Current/Best: 13.80/ 21.13 GFLOPS | Progress: (20/20) | 19.06 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.09/ 19.09 GFLOPS | Progress: (4/20) | 4.56 s
[Task 16/25] Current/Best: 18.94/ 19.09 GFLOPS | Progress: (8/20) | 6.10 s
[Task 16/25] Current/Best: 15.98/ 21.71 GFLOPS | Progress: (12/20) | 8.59 s
[Task 16/25] Current/Best: 9.31/ 21.71 GFLOPS | Progress: (16/20) | 13.10 s
[Task 16/25] Current/Best: 10.41/ 21.71 GFLOPS | Progress: (20/20) | 16.39 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.16/ 12.39 GFLOPS | Progress: (4/20) | 5.79 s
[Task 17/25] Current/Best: 11.78/ 12.39 GFLOPS | Progress: (8/20) | 8.78 s
[Task 17/25] Current/Best: 3.08/ 23.59 GFLOPS | Progress: (12/20) | 12.64 s
[Task 17/25] Current/Best: 21.79/ 23.59 GFLOPS | Progress: (16/20) | 16.49 s
[Task 17/25] Current/Best: 11.82/ 23.59 GFLOPS | Progress: (20/20) | 19.12 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 7.21/ 14.72 GFLOPS | Progress: (4/20) | 6.35 s
[Task 18/25] Current/Best: 9.76/ 20.70 GFLOPS | Progress: (8/20) | 10.10 s
[Task 18/25] Current/Best: 15.49/ 20.70 GFLOPS | Progress: (12/20) | 14.76 s
[Task 18/25] Current/Best: 7.14/ 20.70 GFLOPS | Progress: (16/20) | 17.57 s
[Task 18/25] Current/Best: 21.18/ 21.80 GFLOPS | Progress: (20/20) | 19.58 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 1.56/ 18.73 GFLOPS | Progress: (4/20) | 6.81 s
[Task 19/25] Current/Best: 10.42/ 20.82 GFLOPS | Progress: (8/20) | 9.81 s
[Task 19/25] Current/Best: 3.09/ 20.82 GFLOPS | Progress: (12/20) | 14.87 s
[Task 19/25] Current/Best: 11.53/ 20.82 GFLOPS | Progress: (16/20) | 18.98 s
[Task 19/25] Current/Best: 10.38/ 20.82 GFLOPS | Progress: (20/20) | 23.74 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 14.78/ 15.35 GFLOPS | Progress: (4/20) | 5.30 s
[Task 20/25] Current/Best: 15.51/ 15.51 GFLOPS | Progress: (8/20) | 7.62 s
[Task 20/25] Current/Best: 7.46/ 15.51 GFLOPS | Progress: (12/20) | 11.49 s
[Task 20/25] Current/Best: 7.22/ 19.22 GFLOPS | Progress: (16/20) | 14.49 s
[Task 20/25] Current/Best: 6.84/ 19.22 GFLOPS | Progress: (20/20) | 17.51 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (4/20) | 5.93 s Done.
+
[Task 21/25] Current/Best: 9.30/ 18.80 GFLOPS | Progress: (8/20) | 8.85 s
[Task 21/25] Current/Best: 22.04/ 22.04 GFLOPS | Progress: (12/20) | 11.07 s
[Task 21/25] Current/Best: 8.40/ 22.04 GFLOPS | Progress: (16/20) | 16.63 s
[Task 21/25] Current/Best: 8.66/ 22.04 GFLOPS | Progress: (20/20) | 18.72 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 18.07/ 19.52 GFLOPS | Progress: (4/20) | 5.83 s
[Task 22/25] Current/Best: 12.88/ 19.52 GFLOPS | Progress: (8/20) | 8.58 s
[Task 22/25] Current/Best: 2.76/ 19.52 GFLOPS | Progress: (12/20) | 10.54 s
[Task 22/25] Current/Best: 5.15/ 19.52 GFLOPS | Progress: (16/20) | 12.32 s
[Task 22/25] Current/Best: 10.31/ 19.62 GFLOPS | Progress: (20/20) | 14.96 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.30/ 17.48 GFLOPS | Progress: (4/20) | 5.23 s
[Task 23/25] Current/Best: 9.65/ 17.48 GFLOPS | Progress: (8/20) | 8.47 s
[Task 23/25] Current/Best: 17.69/ 17.69 GFLOPS | Progress: (12/20) | 11.98 s
[Task 23/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (16/20) | 14.76 s
[Task 23/25] Current/Best: 19.68/ 19.68 GFLOPS | Progress: (20/20) | 17.75 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 1.24/ 2.97 GFLOPS | Progress: (4/20) | 13.55 s
[Task 24/25] Current/Best: 2.86/ 2.97 GFLOPS | Progress: (8/20) | 26.05 s
[Task 24/25] Current/Best: 6.75/ 6.75 GFLOPS | Progress: (12/20) | 38.46 s
[Task 24/25] Current/Best: 3.32/ 6.75 GFLOPS | Progress: (16/20) | 49.49 s
[Task 24/25] Current/Best: 3.43/ 6.75 GFLOPS | Progress: (20/20) | 59.88 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 8.66/ 9.36 GFLOPS | Progress: (4/20) | 15.21 s
[Task 25/25] Current/Best: 3.01/ 9.36 GFLOPS | Progress: (8/20) | 19.09 s
[Task 25/25] Current/Best: 3.02/ 9.36 GFLOPS | Progress: (12/20) | 25.08 s
[Task 25/25] Current/Best: 1.55/ 9.36 GFLOPS | Progress: (16/20) | 36.06 s
[Task 25/25] Current/Best: 8.57/ 9.36 GFLOPS | Progress: (2
0/20) | 38.78 s
@@ -702,8 +700,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -760,8 +758,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 384.0942227599953, 'median': 384.69915269998864, 'std': 1.9332749642127023}
- unoptimized: {'mean': 516.0434589399995, 'median': 516.7266176999988, 'std': 1.4996019181741262}
+ optimized: {'mean': 415.24757281997154, 'median': 415.3037009999025, 'std': 0.714092807443414}
+ unoptimized: {'mean': 513.4662605699486, 'median': 513.2093307500327, 'std': 2.184630412673929}
@@ -784,7 +782,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 3.951 seconds)
+ **Total running time of the script:** ( 13 minutes 8.340 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 8dea257c2b..3ff31f3a9d 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
- 1.265e-07 secs/op
+ 1.25e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 41502be69c..ef0230a69d 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, 0xf006a20)), stage(b, placeholder(b, 0x228c8ba0)), 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, 0x248678b0)), stage(b, placeholder(b, 0x174fc9f0)), 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 3898e35125..6cf3aab148 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
=================
-**15:57.819** total execution time for **tutorial** files:
+**16:49.567** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:03.951 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 13:08.340 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:33.151 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:31.405 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.231 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.612 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:42.786 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:38.012 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.884 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:30.411 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.791 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.879 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.857 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.731 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.168 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.178 | 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 e8dd6eb730..adb338af92 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -286,7 +286,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000007
- naive: 0.000009
+ naive: 0.000007
@@ -389,7 +389,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000006
+ parallel: 0.000007
@@ -444,7 +444,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000041
+ vector: 0.000040
# 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 6.527969999297056e-06 1.0
- naive 9.4609e-06 1.449286684990704
- parallel 5.8872e-06 0.9018423798874604
- vector 4.08989e-05 6.265178915406178
+ numpy 7.413980019919109e-06 1.0
+ naive 6.860900000000001e-06 0.9254003897457034
+ parallel 7.2788000000000005e-06 0.9817668756112209
+ vector 4.04225e-05 5.452199748501755
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.015286
+ Numpy running time: 0.018400
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.275038
+ none: 3.247699
@@ -1080,7 +1080,7 @@ schedule.
.. code-block:: none
- blocking: 0.290459
+ blocking: 0.310820
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.326114
+ vectorization: 0.337981
# 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: 0.112610
+ loop permutation: 0.120136
# 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: 0.105976
+ array packing: 0.110148
# 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: 0.098557
+ block caching: 0.111110
# 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: 0.130337
+ parallelization: 0.144702
# 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 3.2750378463000005 1.0
- blocking 0.290458601 0.08868862426373113
- vectorization 0.3261143877 0.09957576156514658
- loop permutation 0.1126095973 0.034384212514436
- array packing 0.10597573580000001 0.03235862935743687
- block caching 0.09855674519999999 0.0300933148944661
- parallelization 0.1303365715 0.039796966513608006
+ none 3.2476994102 1.0
+ blocking 0.3108197049 0.09570457903949278
+ vectorization 0.3379811444 0.10406786519051232
+ loop permutation 0.12013553810000002 0.03699096588886649
+ array packing 0.1101475325 0.03391555639480099
+ block caching 0.11111027440000001 0.034211994512496346
+ parallelization 0.14470213699999998 0.044555273971949555
diff --git a/docs/commit_hash b/docs/commit_hash
index 5efb4a523a..ca7ad91aed 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-cc8cce50fabb5a92e5830bb81b5fa96fb613a698
+4d37a0a078435cd36c56112ee0ee21b3d6bb8bd0
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 7de89d7ebc..6e7252663b 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 24.094 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 25.129 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 8c7a2c5a2f..4a82e0d73d 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.zipf1ab620a-377c-44b7-a2db-8c20125f8734 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.zip98fe92e9-da98-4da2-b68b-52f7ba8db68e 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 f035f3b396..da05e4fa95 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -454,13 +454,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 45.6MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 43.9MB/s]
- 51%|#####1 | 21.2M/41.5M [00:00<00:00, 53.1MB/s]
- 64%|######4 | 26.6M/41.5M [00:00<00:00, 46.2MB/s]
- 82%|########2 | 34.1M/41.5M [00:00<00:00, 43.7MB/s]
- 93%|#########2| 38.5M/41.5M [00:00<00:00, 37.4MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 41.5MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:00, 54.7MB/s]
+ 28%|##7 | 11.5M/41.5M [00:00<00:00, 46.3MB/s]
+ 39%|###8 | 16.0M/41.5M [00:00<00:00, 28.2MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 33.2MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.2MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 39.3MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 38.3MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 0a1eeb1813..47f2ce80e4 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -437,10 +437,15 @@ 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]
- 30%|##9 | 13.3M/44.7M [00:00<00:00, 139MB/s]
- 59%|#####9 | 26.5M/44.7M [00:00<00:00, 86.0MB/s]
- 80%|######## | 35.8M/44.7M [00:00<00:00, 89.5MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 85.3MB/s]
+ 14%|#4 | 6.30M/44.7M [00:00<00:00, 56.8MB/s]
+ 26%|##6 | 11.7M/44.7M [00:00<00:00, 53.5MB/s]
+ 38%|###7 | 16.8M/44.7M [00:00<00:00, 39.5MB/s]
+ 54%|#####3 | 24.1M/44.7M [00:00<00:00, 50.1MB/s]
+ 68%|######7 | 30.3M/44.7M [00:00<00:00, 45.5MB/s]
+ 78%|#######8 | 35.0M/44.7M [00:00<00:00, 44.3MB/s]
+ 88%|########8 | 39.4M/44.7M [00:00<00:00, 42.6MB/s]
+ 98%|#########7| 43.6M/44.7M [00:01<00:00, 31.8MB/s]
+100%|##########| 44.7M/44.7M [00:01<00:00, 40.3MB/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 8980f6cd14..37868ff342 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 31.816 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.016 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 af7b8e44a6..7c1f701df7 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:59.655</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>07:02.123</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>01:31.816</p></td>
+<td><p>01:30.016</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>01:24.094</p></td>
+<td><p>01:25.129</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>00:59.034</p></td>
+<td><p>00:57.752</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>00:39.219</p></td>
+<td><p>00:38.942</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>00:32.758</p></td>
+<td><p>00:33.631</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>00:30.428</p></td>
+<td><p>00:31.288</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>00:28.962</p></td>
+<td><p>00:30.105</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>00:26.166</p></td>
+<td><p>00:27.214</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:24.461</p></td>
+<td><p>00:25.228</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>00:02.717</p></td>
+<td><p>00:02.820</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 7afd69f831..cd607244ea 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -835,7 +835,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2540.4115 2540.1485 2543.9367 2537.6377 1.7478
+ 2545.6327 2545.1691 2547.9848 2544.0202 1.3874
</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 33f3bade09..de98f7251f 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
@@ -443,30 +443,21 @@ 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
- 5439488/102967424 [>.............................] - ETA: 1s
- 8380416/102967424 [=>............................] - ETA: 2s
- 16769024/102967424 [===>..........................] - ETA: 1s
- 24748032/102967424 [======>.......................] - ETA: 1s
- 25157632/102967424 [======>.......................] - ETA: 1s
- 33546240/102967424 [========>.....................] - ETA: 1s
- 40189952/102967424 [==========>...................] - ETA: 1s
- 41934848/102967424 [===========>..................] - ETA: 1s
+ 8380416/102967424 [=>............................] - ETA: 0s
+ 16769024/102967424 [===>..........................] - ETA: 0s
+ 23396352/102967424 [=====>........................] - ETA: 0s
+ 26484736/102967424 [======>.......................] - ETA: 0s
+ 33546240/102967424 [========>.....................] - ETA: 0s
+ 41934848/102967424 [===========>..................] - ETA: 0s
50323456/102967424 [=============>................] - ETA: 0s
- 56967168/102967424 [===============>..............] - ETA: 0s
58712064/102967424 [================>.............] - ETA: 0s
- 65355776/102967424 [==================>...........] - ETA: 0s
67100672/102967424 [==================>...........] - ETA: 0s
- 69296128/102967424 [===================>..........] - ETA: 0s
75489280/102967424 [====================>.........] - ETA: 0s
- 82124800/102967424 [======================>.......] - ETA: 0s
83877888/102967424 [=======================>......] - ETA: 0s
- 84017152/102967424 [=======================>......] - ETA: 0s
90521600/102967424 [=========================>....] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
- 99098624/102967424 [===========================>..] - ETA: 0s
-100646912/102967424 [============================>.] - ETA: 0s
-102850560/102967424 [============================>.] - ETA: 0s
-102967424/102967424 [==============================] - 2s 0us/step
+100392960/102967424 [============================>.] - ETA: 0s
+102967424/102967424 [==============================] - 1s 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 cd62ec0a80..050bb341ea 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)
- 14.3295 14.2650 14.6626 14.1360 0.1888
+ 16.7394 16.5290 17.6822 16.3120 0.4470
</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 d341feefa5..c6b0365099 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -459,34 +459,35 @@ 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<00:03, 48.6MB/s]
- 6%|6 | 10.9M/170M [00:00<00:04, 38.6MB/s]
- 9%|8 | 14.7M/170M [00:00<00:04, 37.1MB/s]
- 11%|# | 18.2M/170M [00:00<00:04, 34.1MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:04, 35.4MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:03, 36.9MB/s]
- 24%|##3 | 40.0M/170M [00:01<00:03, 40.7MB/s]
- 27%|##7 | 46.3M/170M [00:01<00:02, 43.8MB/s]
- 30%|##9 | 50.5M/170M [00:01<00:02, 42.6MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 43.9MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:02, 47.1MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:01, 54.8MB/s]
- 46%|####6 | 78.3M/170M [00:01<00:01, 52.2MB/s]
- 49%|####9 | 83.4M/170M [00:01<00:01, 49.4MB/s]
- 52%|#####1 | 88.2M/170M [00:02<00:02, 40.3MB/s]
- 57%|#####6 | 96.0M/170M [00:02<00:01, 43.0MB/s]
- 61%|######1 | 104M/170M [00:02<00:01, 41.9MB/s]
- 66%|######5 | 112M/170M [00:02<00:01, 43.0MB/s]
- 71%|####### | 120M/170M [00:02<00:01, 47.5MB/s]
- 75%|#######5 | 128M/170M [00:03<00:00, 50.9MB/s]
- 80%|######## | 136M/170M [00:03<00:00, 40.8MB/s]
- 85%|########4 | 144M/170M [00:03<00:00, 45.9MB/s]
- 88%|########8 | 150M/170M [00:03<00:00, 47.0MB/s]
- 91%|#########1| 155M/170M [00:03<00:00, 46.5MB/s]
- 94%|#########4| 160M/170M [00:03<00:00, 39.7MB/s]
- 96%|#########6| 164M/170M [00:03<00:00, 38.3MB/s]
- 99%|#########8| 168M/170M [00:04<00:00, 39.4MB/s]
-100%|##########| 170M/170M [00:04<00:00, 43.3MB/s]
+ 4%|3 | 6.30M/170M [00:00<00:03, 46.9MB/s]
+ 6%|6 | 10.8M/170M [00:00<00:04, 40.9MB/s]
+ 9%|8 | 14.7M/170M [00:00<00:04, 35.7MB/s]
+ 11%|# | 18.1M/170M [00:00<00:05, 31.4MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:05, 27.7MB/s]
+ 17%|#6 | 28.4M/170M [00:00<00:04, 31.6MB/s]
+ 19%|#8 | 32.0M/170M [00:01<00:05, 28.9MB/s]
+ 24%|##3 | 40.0M/170M [00:01<00:03, 36.0MB/s]
+ 28%|##8 | 47.9M/170M [00:01<00:02, 46.3MB/s]
+ 32%|###1 | 54.3M/170M [00:01<00:02, 51.3MB/s]
+ 35%|###5 | 59.6M/170M [00:01<00:02, 47.4MB/s]
+ 38%|###7 | 64.5M/170M [00:01<00:02, 42.6MB/s]
+ 42%|####2 | 72.0M/170M [00:01<00:02, 42.9MB/s]
+ 47%|####7 | 80.0M/170M [00:02<00:02, 45.2MB/s]
+ 51%|##### | 86.3M/170M [00:02<00:01, 45.6MB/s]
+ 53%|#####3 | 90.7M/170M [00:02<00:02, 41.4MB/s]
+ 57%|#####6 | 96.0M/170M [00:02<00:02, 38.3MB/s]
+ 60%|###### | 102M/170M [00:02<00:01, 39.6MB/s]
+ 62%|######2 | 106M/170M [00:02<00:01, 37.2MB/s]
+ 66%|######5 | 112M/170M [00:03<00:01, 36.8MB/s]
+ 71%|####### | 120M/170M [00:03<00:01, 38.3MB/s]
+ 75%|#######5 | 128M/170M [00:03<00:01, 41.6MB/s]
+ 80%|######## | 136M/170M [00:03<00:00, 37.6MB/s]
+ 85%|########4 | 144M/170M [00:03<00:00, 42.4MB/s]
+ 88%|########8 | 150M/170M [00:03<00:00, 42.0MB/s]
+ 91%|######### | 154M/170M [00:04<00:00, 41.5MB/s]
+ 94%|#########4| 160M/170M [00:04<00:00, 41.2MB/s]
+ 98%|#########7| 166M/170M [00:04<00:00, 42.3MB/s]
+100%|##########| 170M/170M [00:04<00:00, 39.8MB/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=& [...]
@@ -584,7 +585,7 @@ 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 28.645 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 51.087 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 49437c84c8..53dd76938c 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -500,9 +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]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 48.0MB/s]
- 93%|#########2| 12.6M/13.6M [00:00<00:00, 47.2MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 50.3MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 75.6MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 80.6MB/s]
</pre></div>
</div>
</div>
@@ -593,7 +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)
- 87.9646 87.8905 90.1300 87.6707 0.2985
+ 90.8449 90.7368 94.5931 90.4194 0.5807
</pre></div>
</div>
<div class="admonition note">
@@ -632,7 +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 16.760 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.510 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 41f6139613..3ca37367e3 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)
- 117.2412 117.3870 119.4369 115.0188 1.0573
+ 120.9982 120.5474 153.8192 119.5517 3.3442
</pre></div>
</div>
<div class="admonition note">
@@ -613,7 +613,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 35.548 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 39.539 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 8746c26b9d..64036a7c5d 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 49.527 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 7.367 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 8dcde3b572..39d237f5f4 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -468,24 +468,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6468/132723 [00:00<00:01, 64671.43KB/s]
- 11%|# | 14523/132723 [00:00<00:01, 74003.20KB/s]
- 17%|#6 | 21924/132723 [00:00<00:01, 68208.73KB/s]
- 23%|##2 | 29968/132723 [00:00<00:01, 72799.27KB/s]
- 29%|##8 | 37946/132723 [00:00<00:01, 75229.80KB/s]
- 35%|###4 | 45957/132723 [00:00<00:01, 76847.84KB/s]
- 41%|#### | 53949/132723 [00:00<00:01, 77835.91KB/s]
- 47%|####6 | 61970/132723 [00:00<00:00, 78559.77KB/s]
- 53%|#####2 | 69843/132723 [00:01<00:01, 56117.19KB/s]
- 59%|#####8 | 77696/132723 [00:01<00:00, 61498.47KB/s]
- 64%|######3 | 84603/132723 [00:01<00:00, 61254.61KB/s]
- 70%|######9 | 92555/132723 [00:01<00:00, 66016.02KB/s]
- 75%|#######5 | 99600/132723 [00:01<00:00, 56541.97KB/s]
- 81%|######## | 107491/132723 [00:01<00:00, 62041.22KB/s]
- 86%|########6 | 114680/132723 [00:01<00:00, 52938.02KB/s]
- 91%|######### | 120526/132723 [00:01<00:00, 49061.84KB/s]
- 97%|#########6| 128361/132723 [00:02<00:00, 55846.31KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 62717.12KB/s]
+ 5%|5 | 7074/132723 [00:00<00:01, 70718.82KB/s]
+ 11%|#1 | 15152/132723 [00:00<00:01, 59955.16KB/s]
+ 16%|#6 | 21290/132723 [00:00<00:02, 52803.86KB/s]
+ 22%|##2 | 29711/132723 [00:00<00:01, 63189.52KB/s]
+ 27%|##7 | 36293/132723 [00:00<00:01, 51505.17KB/s]
+ 34%|###3 | 44680/132723 [00:00<00:01, 60220.85KB/s]
+ 39%|###9 | 52245/132723 [00:00<00:01, 64507.77KB/s]
+ 46%|####5 | 60675/132723 [00:00<00:01, 70130.45KB/s]
+ 52%|#####2 | 69060/132723 [00:01<00:00, 74088.74KB/s]
+ 58%|#####8 | 77430/132723 [00:01<00:00, 76894.15KB/s]
+ 64%|######4 | 85324/132723 [00:01<00:00, 68011.74KB/s]
+ 71%|####### | 93693/132723 [00:01<00:00, 72235.86KB/s]
+ 76%|#######6 | 101191/132723 [00:01<00:00, 51077.37KB/s]
+ 83%|########2 | 109536/132723 [00:01<00:00, 58116.86KB/s]
+ 88%|########7 | 116328/132723 [00:01<00:00, 52783.27KB/s]
+ 94%|#########3| 124668/132723 [00:02<00:00, 59769.98KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 62573.55KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -524,7 +523,7 @@ 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> ( 4 minutes 3.000 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> ( 4 minutes 10.126 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 846e3cd3e9..cd14abe529 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>16:43.012</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>17:48.372</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>04:03.000</p></td>
+<td><p>04:10.126</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>03:28.645</p></td>
+<td><p>03:51.087</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:35.548</p></td>
+<td><p>02:39.539</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>01:49.527</p></td>
+<td><p>02:07.367</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>01:16.760</p></td>
+<td><p>01:21.510</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>00:55.460</p></td>
+<td><p>00:56.628</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>00:53.915</p></td>
+<td><p>00:54.138</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:43.004</p></td>
+<td><p>00:47.615</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>00:28.792</p></td>
+<td><p>00:30.534</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:28.355</p></td>
+<td><p>00:29.823</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 d3cc3fb1d3..08b6844599 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.zipc7319429-031b-4429-996e-d4d371792dae 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.zip03cbc4e5-669d-4717-a946-baf098d40e36 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 24ddcb8ba0..e075cfa77e 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>00:55.623</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:57.290</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>00:51.751</p></td>
+<td><p>00:53.336</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.787</p></td>
+<td><p>00:02.836</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>00:01.077</p></td>
+<td><p>00:01.110</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 735b879e08..116c4627a5 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: 23018us [23018us] (48.77%; 48.77%)
-FoldScaleAxis: 24176us [6us] (51.23%; 51.23%)
- FoldConstant: 24170us [1694us] (51.21%; 99.98%)
- InferType: 22476us [22476us] (47.62%; 92.99%)
+InferType: 23317us [23317us] (48.46%; 48.46%)
+FoldScaleAxis: 24803us [10us] (51.54%; 51.54%)
+ FoldConstant: 24793us [1726us] (51.52%; 99.96%)
+ InferType: 23066us [23066us] (47.94%; 93.04%)
</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: 22780us [22780us] (48.42%; 48.42%)
-FoldScaleAxis: 24269us [5us] (51.58%; 51.58%)
- FoldConstant: 24264us [1667us] (51.57%; 99.98%)
- InferType: 22597us [22597us] (48.03%; 93.13%)
+InferType: 22949us [22949us] (48.46%; 48.46%)
+FoldScaleAxis: 24405us [7us] (51.54%; 51.54%)
+ FoldConstant: 24399us [1751us] (51.52%; 99.97%)
+ InferType: 22647us [22647us] (47.83%; 92.82%)
</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 ec8ad5b916..2f220041c3 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: 47.613918 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.940990 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 be224f7d70..363b7ee669 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -862,7 +862,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.241196 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.796375 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 1ce92090ae..f08b12c578 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: 0.017968
-Baseline: 3.300610
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018450
+Baseline: 3.284330
</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: 0.301371
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.316429
</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: 0.346604
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.353612
</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: 0.113008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115747
</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: 0.108601
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109961
</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: 0.110817
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111417
</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: 0.146270
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148707
</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 fae0ad136b..2e5344ad7e 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>00:34.965</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.826</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.032</p></td>
+<td><p>00:32.517</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>00:01.836</p></td>
+<td><p>00:02.058</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>00:01.097</p></td>
+<td><p>00:01.252</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 36a408361a..603d78fec3 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:30.016</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>10:29.707</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>06:30.327</p></td>
+<td><p>06:23.264</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>01:45.242</p></td>
+<td><p>01:47.776</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>01:12.763</p></td>
+<td><p>01:14.288</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:33.363</p></td>
+<td><p>00:35.109</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:14.472</p></td>
+<td><p>00:14.990</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>00:13.850</p></td>
+<td><p>00:14.282</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 3e8ce3e597..25a7b42592 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 +510,317 @@ 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", 112)
- conv2d_nchw = T.allocate([4], "float32", "local")
- pad_temp_shared = T.allocate([36], "float32", "shared")
- kernel_shared = T.allocate([384], "float32", "shared")
+ blockIdx_x = T.launch_thread("blockIdx.x", 32)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([162], "float32", "shared")
+ kernel_shared = T.allocate([288], "float32", "shared")
threadIdx_x = T.launch_thread("threadIdx.x", 56)
conv2d_nchw_1 = T.Buffer((4,), data=conv2d_nchw, scope="local", align=8)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(128, 3):
- cse_var_2: T.int32 = rc_outer_outer * 36
- cse_var_1: T.int32 = ry_outer_outer * 3
- pad_temp_shared_1 = T.Buffer((36,), data=pad_temp_shared, scope="shared")
- with T.launch_thread("threadIdx.x", 56) as threadIdx_x_1:
- if T.likely(threadIdx_x_1 < 36):
- data_1 = T.Buffer((25088,), data=data.data)
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[rc_outer_outer * 196 + threadIdx_x_1 // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[13] = T.float32(0)
+ for rc_outer_outer in range(256):
+ cse_var_2: T.int32 = rc_outer_outer * 98
+ cse_var_1: T.int32 = rc_outer_outer * 18
threadIdx_x_1 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((384,), data=kernel_shared, scope="shared")
- kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x // 7 * 147456 + threadIdx_x_1 // 12 * 4608 + cse_var_2 + threadIdx_x_1 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[(threadIdx_x_1 + 56) // 12 * 12 + (threadIdx_x_1 + 8) % 12 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 147456 + (threadIdx_x_1 + 56) // 12 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
- with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[(threadIdx_x_1 + 112) // 12 * 12 + (threadIdx_x_1 + 4) % 12 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 147456 + (threadIdx_x_1 + 112) // 12 * 4608 + cse_var_2 + (threadIdx_x_1 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ pad_temp_shared_1 = T.Buffer((162,), data=pad_temp_shared, scope="shared")
+ data_1 = T.Buffer((25088,), data=data.data)
with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[threadIdx_x_1 + 168] = kernel_1[blockIdx_x // 7 * 147456 + threadIdx_x_1 // 12 * 4608 + cse_var_2 + threadIdx_x_1 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 64512]
+ pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + threadIdx_x_1 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[(threadIdx_x_1 + 224) // 12 * 12 + (threadIdx_x_1 + 8) % 12 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 147456 + (threadIdx_x_1 + 224) // 12 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ pad_temp_shared_1[threadIdx_x_1 + 56] = T.if_then_else(9 <= (threadIdx_x_1 + 56) % 81 and (threadIdx_x_1 + 56) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 56) // 81 * 49 + (threadIdx_x_1 + 56) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
with T.launch_thread(threadIdx_x_1, 56):
- kernel_shared_1[(threadIdx_x_1 + 280) // 12 * 12 + (threadIdx_x_1 + 4) % 12 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 147456 + (threadIdx_x_1 + 280) // 12 * 4608 + cse_var_2 + (threadIdx_x_1 + 4) % 12 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
- with T.launch_thread(threadIdx_x_1, 56):
- if T.likely(threadIdx_x_1 < 48):
- kernel_shared_1[threadIdx_x_1 + 336] = kernel_1[blockIdx_x // 7 * 147456 + threadIdx_x_1 // 12 * 4608 + cse_var_2 + threadIdx_x_1 % 12 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 129024]
- for rx_outer_inner in range(3):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 192]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 12]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 204]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 195]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 15]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 207]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 6]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 198]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 18]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 210]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 9]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 201]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 21]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rx_outer_inner + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 24 + rx_outer_inner + 213]
+ if T.likely(threadIdx_x_1 < 50):
+ pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(threadIdx_x_1 < 41 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 81 * 49 + (threadIdx_x_1 + 31) // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
+ threadIdx_x_2 = T.env_thread("threadIdx.x")
+ kernel_shared_1 = T.Buffer((288,), data=kernel_shared, scope="shared")
+ kernel_1 = T.Buffer((2359296,), data=kernel.data)
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + threadIdx_x_2 // 18 * 4608 + cse_var_1 + threadIdx_x_2 % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 56] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 56) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 + 2) % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 112] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 112) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 + 4) % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 168] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 168) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 + 6) % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ kernel_shared_1[threadIdx_x_2 + 224] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 224) // 18 * 4608 + cse_var_1 + (threadIdx_x_2 + 8) % 18]
+ with T.launch_thread(threadIdx_x_2, 56):
+ if T.likely(threadIdx_x_2 < 8):
+ kernel_shared_1[threadIdx_x_2 + 280] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 280) // 18 * 4608 + cse_var_1 + threadIdx_x_2 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 36 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 36 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 36 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 36 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 9] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 10] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 9] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 10] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 10] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 16] * kernel_shared_1[threadIdx_x // 7 * 36 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 10] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 16] * kernel_shared_1[threadIdx_x // 7 * 36 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 16] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 17] * kernel_shared_1[threadIdx_x // 7 * 36 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 11] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 12] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 13] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 14] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 15] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 16] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 17] * kernel_shared_1[threadIdx_x // 7 * 36 + 23]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 18] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 19] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 18] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 19] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 19] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 25] * kernel_shared_1[threadIdx_x // 7 * 36 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 19] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 25] * kernel_shared_1[threadIdx_x // 7 * 36 + 25]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 25] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 26] * kernel_shared_1[threadIdx_x // 7 * 36 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 20] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 21] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 22] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 23] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 24] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 25] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 26] * kernel_shared_1[threadIdx_x // 7 * 36 + 26]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 81] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 82] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 81] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 82] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 82] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 88] * kernel_shared_1[threadIdx_x // 7 * 36 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 82] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 88] * kernel_shared_1[threadIdx_x // 7 * 36 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 88] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 89] * kernel_shared_1[threadIdx_x // 7 * 36 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 83] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 84] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 85] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 86] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 87] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 88] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 89] * kernel_shared_1[threadIdx_x // 7 * 36 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 90] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 91] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 90] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 91] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 30]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 91] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 97] * kernel_shared_1[threadIdx_x // 7 * 36 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 91] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 97] * kernel_shared_1[threadIdx_x // 7 * 36 + 31]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 97] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 98] * kernel_shared_1[threadIdx_x // 7 * 36 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 92] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 93] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 94] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 95] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 96] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 97] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 98] * kernel_shared_1[threadIdx_x // 7 * 36 + 32]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 99] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 100] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 99] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 100] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 100] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 106] * kernel_shared_1[threadIdx_x // 7 * 36 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 100] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 106] * kernel_shared_1[threadIdx_x // 7 * 36 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 106] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 107] * kernel_shared_1[threadIdx_x // 7 * 36 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 101] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 102] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 103] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 104] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 105] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 106] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[threadIdx_x % 7 * 9 + 107] * kernel_shared_1[threadIdx_x // 7 * 36 + 35]
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 // 7 * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x // 7 * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_1[blockIdx_x // 7 * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + threadIdx_x % 7 + 784] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x // 7 * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7] = T.max(conv2d_nchw_1[i1_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 1] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 2] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 3] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 4] = T.max(conv2d_nchw_1[i1_inner + 8] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 5] = T.max(conv2d_nchw_1[i1_inner + 10] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 6] = T.max(conv2d_nchw_1[i1_inner + 12] + bias_1[blockIdx_x * 16 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -601,7 +854,7 @@ 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: 0.356 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.368 ms
</pre></div>
</div>
</div>
@@ -633,34 +886,34 @@ conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nch
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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=2)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=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_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_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=7)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=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=2)
+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=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_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+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=7)
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)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -686,7 +939,7 @@ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fus
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=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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -712,52 +965,300 @@ CUDA source code:
#define uint64_t unsigned long long
#endif
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[4];
- __shared__ float pad_temp_shared[36];
- __shared__ float kernel_shared[384];
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[162];
+ __shared__ float kernel_shared[288];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 36) {
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 56) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 112) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((((((int)threadIdx.x) + 224) / 12) * 12) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 8) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((((((int)threadIdx.x) + 280) / 12) * 12) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 280) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((((int)threadIdx.x) + 4) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((((int)blockIdx.x) / 7) * 147456) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + (((((int)threadIdx.x) % 12) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- }
- __syncthreads();
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 24) + rx_outer_inner)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(rx_outer_inner + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 204)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 207)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 210)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rx_outer_inner + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 24) + rx_outer_inner) + 213)]));
- }
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 256; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 98) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 50) {
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = ((((((int)threadIdx.x) < 41) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 98) + (((((int)threadIdx.x) + 112) / 81) * 49)) + (((((int)threadIdx.x) + 31) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 18) * 4608)) + (rc_outer_outer * 18)) + (((int)threadIdx.x) % 18))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 2) % 18))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 4) % 18))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 6) % 18))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 18) * 4608)) + (rc_outer_outer * 18)) + ((((int)threadIdx.x) + 8) % 18))];
+ if (((int)threadIdx.x) < 8) {
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 18) * 4608)) + (rc_outer_outer * 18)) + ((int)threadIdx.x)) + 10)];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 22)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 23)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 24)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 25)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 26)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 84)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 85)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 86)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 87)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 88)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 89)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 93)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 94)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 95)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 96)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 97)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 98)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 102)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 103)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 104)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 105)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 106)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 9) + 107)] * kernel_shared[(((((int)threadIdx.x) / 7) * 36) + 35)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((((int)blockIdx.x) / 7) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((((int)blockIdx.x) / 7) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -792,7 +1293,7 @@ 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 30.327 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 23.264 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 8180af4884..3b3663d38c 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)
- 8.1389 8.1398 8.1586 8.1184 0.0164
+ 8.1081 8.1105 8.1110 8.1028 0.0037
</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 12.763 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.288 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 58685600c7..bd3ea7281c 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)
- 761.2308 754.8867 776.0611 752.7446 10.5230
+ 758.5179 758.6952 758.8663 757.9921 0.3783
</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 45.242 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 47.776 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 2f96399ced..46480626ec 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -637,85 +637,74 @@ 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(128):
- compute_1 = T.allocate([512], "float32", "global")
- compute_2 = T.Buffer((512,), data=compute_1)
- for i_outer_inner in range(32):
- cse_var_2: T.int32 = i_outer_inner * 16
- cse_var_1: T.int32 = i0_outer_i1_outer_fused % 64 // 2
- compute_2[cse_var_2] = T.float32(0)
- compute_2[cse_var_2 + 1] = T.float32(0)
- compute_2[cse_var_2 + 2] = T.float32(0)
- compute_2[cse_var_2 + 3] = T.float32(0)
- compute_2[cse_var_2 + 4] = T.float32(0)
- compute_2[cse_var_2 + 5] = T.float32(0)
- compute_2[cse_var_2 + 6] = T.float32(0)
- compute_2[cse_var_2 + 7] = T.float32(0)
- compute_2[cse_var_2 + 8] = T.float32(0)
- compute_2[cse_var_2 + 9] = T.float32(0)
- compute_2[cse_var_2 + 10] = T.float32(0)
- compute_2[cse_var_2 + 11] = T.float32(0)
- compute_2[cse_var_2 + 12] = T.float32(0)
- compute_2[cse_var_2 + 13] = T.float32(0)
- compute_2[cse_var_2 + 14] = T.float32(0)
- compute_2[cse_var_2 + 15] = T.float32(0)
- for elem_idx in range(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
+ 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 nb_j_inner in range(2):
+ for i_inner_init in range(32):
+ cse_var_1: T.int32 = i_inner_init * 32 + nb_j_inner * 16
+ compute_2[cse_var_1] = T.float32(0)
+ compute_2[cse_var_1 + 1] = T.float32(0)
+ compute_2[cse_var_1 + 2] = T.float32(0)
+ compute_2[cse_var_1 + 3] = T.float32(0)
+ compute_2[cse_var_1 + 4] = T.float32(0)
+ compute_2[cse_var_1 + 5] = T.float32(0)
+ compute_2[cse_var_1 + 6] = T.float32(0)
+ compute_2[cse_var_1 + 7] = T.float32(0)
+ compute_2[cse_var_1 + 8] = T.float32(0)
+ compute_2[cse_var_1 + 9] = T.float32(0)
+ compute_2[cse_var_1 + 10] = T.float32(0)
+ compute_2[cse_var_1 + 11] = T.float32(0)
+ compute_2[cse_var_1 + 12] = T.float32(0)
+ 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 % 16 * 2 + nb_j_inner}), 32):
+ cse_var_2 = T.int32()
placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_21: T.int32 = elem_idx * 16
+ cse_var_20: T.int32 = i_inner * 32 + nb_j_inner * 16
+ cse_var_19: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_18: T.int32 = i0_outer_i1_outer_fused // 16 * 8192 + i_inner * 256
+ cse_var_17: T.int32 = cse_var_20 + 9
+ cse_var_16: T.int32 = cse_var_20 + 8
+ cse_var_15: T.int32 = cse_var_20 + 7
+ cse_var_14: T.int32 = cse_var_20 + 6
+ cse_var_13: T.int32 = cse_var_20 + 5
+ cse_var_12: T.int32 = cse_var_20 + 4
+ cse_var_11: T.int32 = cse_var_20 + 3
+ cse_var_10: T.int32 = cse_var_20 + 2
+ cse_var_9: T.int32 = cse_var_20 + 15
+ cse_var_8: T.int32 = cse_var_20 + 14
+ cse_var_7: T.int32 = cse_var_20 + 13
+ cse_var_6: T.int32 = cse_var_20 + 12
+ cse_var_5: T.int32 = cse_var_20 + 11
+ cse_var_4: T.int32 = cse_var_20 + 10
+ cse_var_3: T.int32 = cse_var_20 + 1
placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
placeholder_7 = T.Buffer((32768,), data=placeholder.data)
placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_3: T.int32 = cse_var_2 + 1
- compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_4: T.int32 = cse_var_2 + 2
- compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_5: T.int32 = cse_var_2 + 3
- compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_6: T.int32 = cse_var_2 + 4
- compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_7: T.int32 = cse_var_2 + 5
- compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_8: T.int32 = cse_var_2 + 6
- compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_9: T.int32 = cse_var_2 + 7
- compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx]], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_10: T.int32 = cse_var_2 + 8
- compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_11: T.int32 = cse_var_2 + 9
- compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 1] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_12: T.int32 = cse_var_2 + 10
- compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 2] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_13: T.int32 = cse_var_2 + 11
- compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 3] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_14: T.int32 = cse_var_2 + 12
- compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 4] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_15: T.int32 = cse_var_2 + 13
- compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 5] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_16: T.int32 = cse_var_2 + 14
- compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 6] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- if T.likely(elem_idx < placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1]):
- cse_var_17: T.int32 = cse_var_2 + 15
- compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_1] * 16 + elem_idx * 16 + i0_outer_i1_outer_fused % 2 * 8 + 7] * T.max(placeholder_7[i0_outer_i1_outer_fused // 64 * 16384 + i_outer_inner * 512 + placeholder_8[placeholder_5[cse_var_1] + elem_idx] + 256], T.float32(0))
- for i0_inner in range(64):
- cse_var_18: T.int32 = i0_outer_i1_outer_fused // 64 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 64 * 8
+ compute_2[cse_var_20] = compute_2[cse_var_20] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_19] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_18 + placeholder_8[placeholder_5[cse_var_19] + elem_idx]], T.float32(0))
+ for i0_inner in range(32):
+ cse_var_22: T.int32 = i0_outer_i1_outer_fused // 16 * 16384 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32
compute_3 = T.Buffer((65536,), data=compute.data)
placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
- compute_3[cse_var_18:cse_var_18 + 8] = T.max(compute_2[i0_inner * 8:i0_inner * 8 + 8] + placeholder_5[cse_var_18:cse_var_18 + 8], T.Broadcast(T.float32(0), 8))
+ compute_3[cse_var_22:cse_var_22 + 32] = T.max(compute_2[i0_inner * 32:i0_inner * 32 + 32] + placeholder_5[cse_var_22:cse_var_22 + 32], T.Broadcast(T.float32(0), 32))
</pre></div>
</div>
</div>
@@ -749,7 +738,7 @@ 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: 2.027 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.757 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 55e9815cf8..713448f36e 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>00:36.689</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:43.897</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,7 +354,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:36.651</p></td>
+<td><p>00:43.859</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>
@@ -362,14 +362,14 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
-<td><p>00:00.005</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 09f8fc583c..1916a8e551 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -573,7 +573,8 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+No: 1 GFLOPS: 272.34/272.34 result: MeasureResult(costs=(0.0008500458167938932,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.174592971801758, timestamp=1683225095.3057506) [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4743550
+No: 2 GFLOPS: 0.00/272.34 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
@@ -695,8 +696,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10211556
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8385369
+No: 3 GFLOPS: 0.00/272.34 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
@@ -818,8 +819,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10129203
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6136379
+No: 4 GFLOPS: 0.00/272.34 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
@@ -941,8 +942,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 16, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,338839
-No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8045517
+No: 5 GFLOPS: 0.00/272.34 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
@@ -1064,8 +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, 1, 8, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,764709
-No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,228621
+No: 6 GFLOPS: 32.79/272.34 result: MeasureResult(costs=(0.0070609998125000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.427013874053955, timestamp=1683225100.0333686) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5479815
+No: 7 GFLOPS: 0.00/272.34 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
@@ -1187,8 +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, 1, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5775929
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8702588
+No: 8 GFLOPS: 0.00/272.34 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
@@ -1310,9 +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, 4, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9385274
-No: 7 GFLOPS: 3.37/3.37 result: MeasureResult(costs=(0.0686225355,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6284170150756836, timestamp=1683156679.621043) [('tile_f', [-1, 2, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2060301
-No: 8 GFLOPS: 0.00/3.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4121321
+No: 9 GFLOPS: 0.00/272.34 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
@@ -1434,8 +1435,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4859951
-No: 9 GFLOPS: 0.00/3.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2950561
+No: 10 GFLOPS: 62.15/272.34 result: MeasureResult(costs=(0.0037250195172413795,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.0271501541137695, timestamp=1683225105.8088949) [('tile_f', [-1, 4, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8432382
+No: 11 GFLOPS: 430.70/430.70 result: MeasureResult(costs=(0.0005375034894736843,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8615736961364746, timestamp=1683225106.6741772) [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8422930
+No: 12 GFLOPS: 0.00/430.70 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
@@ -1557,11 +1560,8 @@ 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, 64, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3993134
-No: 10 GFLOPS: 35.36/35.36 result: MeasureResult(costs=(0.006547736125,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4530391693115234, timestamp=1683156681.5583606) [('tile_f', [-1, 1, 1, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3314876
-No: 11 GFLOPS: 37.19/37.19 result: MeasureResult(costs=(0.006225197235294118,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.674783706665039, timestamp=1683156682.4533904) [('tile_f', [-1, 1, 1, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6241895
-No: 12 GFLOPS: 394.35/394.35 result: MeasureResult(costs=(0.0005870448771929825,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.687148094177246, timestamp=1683156683.2791271) [('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3219490
-No: 13 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2574137
+No: 13 GFLOPS: 0.00/430.70 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
@@ -1683,10 +1683,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9321397
-No: 14 GFLOPS: 51.22/394.35 result: MeasureResult(costs=(0.00451943052,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.4141457080841064, timestamp=1683156687.917114) [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8178190
-No: 15 GFLOPS: 6.69/394.35 result: MeasureResult(costs=(0.0346064795,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.387319326400757, timestamp=1683156688.9063199) [('tile_f', [-1, 64, 1, 1]), ('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, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,985166
-No: 16 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 16, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5128458
+No: 14 GFLOPS: 0.00/430.70 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
@@ -1808,8 +1806,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6309053
-No: 17 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,772493
+No: 15 GFLOPS: 0.00/430.70 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
@@ -1931,8 +1929,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5791806
-No: 18 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 64, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8396788
+No: 16 GFLOPS: 0.00/430.70 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
@@ -2054,8 +2052,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2960797
-No: 19 GFLOPS: 0.00/394.35 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3371207
+No: 17 GFLOPS: 0.00/430.70 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
@@ -2177,8 +2175,271 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10189207
-No: 20 GFLOPS: 222.31/394.35 result: MeasureResult(costs=(0.0010413349607843137,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.628429651260376, timestamp=1683156690.7553368) [('tile_f', [-1, 4, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9490452
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1213036
+No: 18 GFLOPS: 0.00/430.70 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:401
+ 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:387
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:282
+ 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:401
+ 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:387
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:282
+ 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, 8, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9860112
+No: 19 GFLOPS: 0.00/430.70 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 512, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3580729
+No: 20 GFLOPS: 0.00/430.70 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:401
+ 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:387
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:282
+ 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:401
+ 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:387
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:282
+ 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, 1, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3014641
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2217,9 +2478,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3219490
+[('tile_f', [-1, 1, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8422930
Finish loading 20 records
-Time cost of this operator: 0.000969
+Time cost of this operator: 0.000944
</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 a2b3227e5a..5b39711912 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 311.5 98.716 (1, 2, 10, 10, 3) 2 1 [311.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.13 0.992 (1, 6, 10, 10) 1 1 [3.13]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.292 (1, 1, 10, 10, 3) 1 1 [0.923]
-Total_time - 315.553 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.5 98.732 (1, 2, 10, 10, 3) 2 1 [315.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.092 0.968 (1, 6, 10, 10) 1 1 [3.092]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.958 0.3 (1, 1, 10, 10, 3) 1 1 [0.958]
+Total_time - 319.551 - - - - -
</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 137.4 98.115 (1, 6, 10, 10, 1) 2 1 [137.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.72 1.228 (1, 6, 10, 10) 1 1 [1.72]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.92 0.657 (1, 1, 10, 10, 3) 1 1 [0.92]
-Total_time - 140.04 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 184.5 98.341 (1, 1, 10, 10, 6) 2 1 [184.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.115 1.127 (1, 6, 10, 10) 1 1 [2.115]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.998 0.532 (1, 3, 10, 10, 1) 1 1 [0.998]
+Total_time - 187.613 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.737 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 27.707 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 1d114711e2..c7bc4e4da7 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]
- 61%|######1 | 2.09M/3.42M [00:00<00:00, 21.9MB/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 33.8MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 82.9MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -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 19.089 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.334 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 e6bbe3ec4a..43c506306f 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/tmpt420wpnj/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpo7e4iq76/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], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpt420wpnj/images/target contains 8144 images
-/tmp/tmpt420wpnj/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [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/tmpo7e4iq76/images/target contains 8144 images
+/tmp/tmpo7e4iq76/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 - 40s - loss: 0.2036 - accuracy: 0.9255 - val_loss: 0.1181 - val_accuracy: 0.9630 - 40s/epoch - 123ms/step
+328/328 - 41s - loss: 0.2368 - accuracy: 0.9198 - val_loss: 0.1113 - val_accuracy: 0.9626 - 41s/epoch - 124ms/step
Epoch 2/3
-328/328 - 35s - loss: 0.1003 - accuracy: 0.9627 - val_loss: 0.1036 - val_accuracy: 0.9637 - 35s/epoch - 106ms/step
+328/328 - 35s - loss: 0.1048 - accuracy: 0.9607 - val_loss: 0.1822 - val_accuracy: 0.9335 - 35s/epoch - 108ms/step
Epoch 3/3
-328/328 - 35s - loss: 0.0637 - accuracy: 0.9747 - val_loss: 0.1087 - val_accuracy: 0.9671 - 35s/epoch - 106ms/step
+328/328 - 35s - loss: 0.0770 - accuracy: 0.9711 - val_loss: 0.0892 - val_accuracy: 0.9668 - 35s/epoch - 108ms/step
-<keras.callbacks.History object at 0x7f03b740a750>
+<keras.callbacks.History object at 0x7f01b5353d90>
</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 22.337 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 30.507 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 3731500e94..533ca7252a 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>07:30.155</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:47.365</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,34 +354,34 @@
</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>04:22.337</p></td>
+<td><p>04:30.507</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>01:22.737</p></td>
+<td><p>01:27.707</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:19.089</p></td>
+<td><p>01:22.334</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>00:10.632</p></td>
+<td><p>00:10.849</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>00:08.031</p></td>
+<td><p>00:08.277</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>00:07.329</p></td>
+<td><p>00:07.691</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>
+<tr class="row-odd"><td><p><a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">1. microTVM CLI Tool</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">1. microTVM CLI Tool</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></td>
+<tr class="row-even"><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>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 4a6a15c15c..a088d4ff7f 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>00:36.968</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:38.044</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>00:32.258</p></td>
+<td><p>00:33.322</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>00:02.908</p></td>
+<td><p>00:03.017</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>00:01.796</p></td>
+<td><p>00:01.698</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 07966172da..d1e01f0c57 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 0x7effece51950>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7efe0c5473b0>
</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 f68070b77c..d2ee00f3e6 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:09.169</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.458</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,31 +354,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:06.390</p></td>
+<td><p>00:02.687</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>00:01.283</p></td>
+<td><p>00:01.244</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>00:00.615</p></td>
+<td><p>00:00.628</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.596</p></td>
+<td><p>00:00.614</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.133</p></td>
+<td><p>00:00.134</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>00:00.065</p></td>
+<td><p>00:00.064</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.057</p></td>
+<td><p>00:00.058</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 60011897a9..2412542d0d 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -234,17 +234,7 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
-<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
-<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
-</ul>
-</li>
-<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
-</ul>
-</li>
+<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 717b57eb43..1746bf5698 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 88b7796d83..c16e4777f5 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/cc8cce50f/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 cd4cbafaed..af08680627 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/cc8cce50f/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 00999a02f1..16e35380c8 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/cc8cce50f/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 4294c233aa..a96d84b64a 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/cc8cce50f/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 07295fbd5a..114f4479b1 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/cc8cce50f/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 e06dd2d73a..25b08c4279 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/cc8cce50f/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 20b32fcd98..f5cb0331f0 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/cc8cce50f/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 8f747db7f9..d4f873d336 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/cc8cce50f/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 188a4291cb..91f9e0013a 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/cc8cce50f/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 dec0b31011..0cf5958cac 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/cc8cce50f/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 68e2ac06bc..162ef409fa 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/cc8cce50f/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 c7bb19344c..f0f6ef5787 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/cc8cce50f/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 1a8316594f..50a7bc9007 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/cc8cce50f/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 e97b789017..5edf4545cb 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/cc8cce50f/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 68a9876d14..c400d25e24 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/cc8cce50f/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 129d626477..947779c5ee 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/cc8cce50f/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 fd3139c280..e668832e80 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/cc8cce50f/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 a1bae2f589..d8b2fe72cc 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/cc8cce50f/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 9fca06f022..cea9fbea63 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/cc8cce50f/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 11af9fa049..decddd61de 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/cc8cce50f/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 f04a3ca2aa..3fac00f860 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/cc8cce50f/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 bd47e0e315..daeb8c85ac 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/cc8cce50f/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 c5e9cae814..f328ee6d1c 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/cc8cce50f/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L89">ctypes.ts:89</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L95">ctypes.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L53">ctypes.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L169">ctypes.ts:169</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L174">ctypes.ts:174</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L184">ctypes.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L151">ctypes.ts:151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L189">ctypes.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L192">ctypes.ts:192</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L209">ctypes.ts:209</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L37">runtime.ts:37</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L781">runtime.ts:781</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/rpc_server.ts#L38">rpc_server.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L1749">runtime.ts:1749</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L343">runtime.ts:343</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L344">runtime.ts:344</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L345">runtime.ts:345</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L346">runtime.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L347">runtime.ts:347</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L272">runtime.ts:272</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L273">runtime.ts:273</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L277">runtime.ts:277</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L274">runtime.ts:274</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L275">runtime.ts:275</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L276">runtime.ts:276</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L280">runtime.ts:280</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L283">runtime.ts:283</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L281">runtime.ts:281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L282">runtime.ts:282</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L286">runtime.ts:286</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L284">runtime.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L285">runtime.ts:285</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/runtime.ts#L287">runtime.ts:287</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 a4923bb8ca..58b3a1e14b 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/cc8cce50f/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 d53e730842..fb1c891aef 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/cc8cce50f/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 5fc5825578..8249cd58ff 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/cc8cce50f/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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/cc8cce50f/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4d37a0a07/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 0c3d1d9022..f75487c402 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 aa406ce374..70f285b083 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>00:32.062</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:32.917</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,7 +354,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:32.054</p></td>
+<td><p>00:32.910</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index aab5e4d15e..e02de2a9a6 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -588,7 +588,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 33.81s!
+resnet18_v1 inference graph built in 35.11s!
</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 5a11dc7113..34cca4bfe4 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 23.21s!
+yolov3-tiny inference graph built in 24.18s!
</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 e0548ed812..46c4876fc2 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:40.968</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:43.425</strong> total execution time for <strong>topic_vta_tutorials_frontend</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="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:50.663</p></td>
+<td><p>00:52.014</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>00:50.305</p></td>
+<td><p>00:51.411</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 48f8963fe3..e98fadb3f5 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>00:03.256</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.314</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>00:02.773</p></td>
+<td><p>00:02.807</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>00:00.483</p></td>
+<td><p>00:00.507</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 f67d38d597..2239f012c9 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>00:00.809</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.862</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>00:00.417</p></td>
+<td><p>00:00.443</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>00:00.393</p></td>
+<td><p>00:00.419</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 882543eae9..5067101434 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -574,7 +574,7 @@ 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: 92.490 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.221 ms
</pre></div>
</div>
</div>
@@ -646,7 +646,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.151 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.405 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 a248a1e6b1..9998c3c62d 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: 0.51/0.51 result: MeasureResult(costs=(0.5237239936,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.622305393218994, timestamp=1683154987.1998823) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
-No: 2 GFLOPS: 11.94/11.94 result: MeasureResult(costs=(0.02249086,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6137738227844238, timestamp=1683154987.8225126) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
-No: 3 GFLOPS: 13.57/13.57 result: MeasureResult(costs=(0.0197760538,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6246299743652344, timestamp=1683154989.6560426) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
-No: 4 GFLOPS: 0.52/13.57 result: MeasureResult(costs=(0.5169321668,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.494956970214844, timestamp=1683154999.4288502) [('tile_y', [-1, 128]), ('tile_x', [-1, 1])],None,7
-No: 5 GFLOPS: 1.58/13.57 result: MeasureResult(costs=(0.1695864266,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9545950889587402, timestamp=1683155002.5158095) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
-No: 6 GFLOPS: 1.53/13.57 result: MeasureResult(costs=(0.1753377892,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.0516767501831055, timestamp=1683155006.8181026) [('tile_y', [-1, 32]), ('tile_x', [-1, 4])],None,25
-No: 7 GFLOPS: 3.29/13.57 result: MeasureResult(costs=(0.0815368112,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5529429912567139, timestamp=1683155008.3744652) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 8 GFLOPS: 0.88/13.57 result: MeasureResult(costs=(0.30414283000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.098167657852173, timestamp=1683155013.4912431) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 9 GFLOPS: 10.57/13.57 result: MeasureResult(costs=(0.025396922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.609248161315918, timestamp=1683155014.248298) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
-No: 10 GFLOPS: 14.06/14.06 result: MeasureResult(costs=(0.0190886888,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5325667858123779, timestamp=1683155014.8051574) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+No: 1 GFLOPS: 11.61/11.61 result: MeasureResult(costs=(0.0231162082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6543011665344238, timestamp=1683223347.3968215) [('tile_y', [-1, 8]), ('tile_x', [-1, 256])],None,83
+No: 2 GFLOPS: 2.61/11.61 result: MeasureResult(costs=(0.10265298479999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.888545274734497, timestamp=1683223349.29835) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
+No: 3 GFLOPS: 4.38/11.61 result: MeasureResult(costs=(0.06124216280000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.254276990890503, timestamp=1683223351.8523116) [('tile_y', [-1, 8]), ('tile_x', [-1, 16])],None,43
+No: 4 GFLOPS: 0.50/11.61 result: MeasureResult(costs=(0.5349444489999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.807214260101318, timestamp=1683223361.9789934) [('tile_y', [-1, 32]), ('tile_x', [-1, 1])],None,5
+No: 5 GFLOPS: 1.39/11.61 result: MeasureResult(costs=(0.19252363960000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.309635639190674, timestamp=1683223365.7692535) [('tile_y', [-1, 1]), ('tile_x', [-1, 1])],None,0
+No: 6 GFLOPS: 11.57/11.61 result: MeasureResult(costs=(0.023198192200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6228973865509033, timestamp=1683223366.4096155) [('tile_y', [-1, 4]), ('tile_x', [-1, 512])],None,92
+No: 7 GFLOPS: 8.96/11.61 result: MeasureResult(costs=(0.029950314999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.0795331001281738, timestamp=1683223368.450017) [('tile_y', [-1, 16]), ('tile_x', [-1, 128])],None,74
+No: 8 GFLOPS: 11.62/11.62 result: MeasureResult(costs=(0.0230984046,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6422500610351562, timestamp=1683223369.0853057) [('tile_y', [-1, 4]), ('tile_x', [-1, 256])],None,82
+No: 9 GFLOPS: 11.49/11.62 result: MeasureResult(costs=(0.0233708374,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.60260009765625, timestamp=1683223369.8020158) [('tile_y', [-1, 128]), ('tile_x', [-1, 32])],None,57
+No: 10 GFLOPS: 11.66/11.66 result: MeasureResult(costs=(0.0230168966,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.59712815284729, timestamp=1683223370.4319348) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
</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 4d84ffe0af..a49b185219 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': 516.0434589399995, 'median': 516.7266176999988, 'std': 1.4996019181741262}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 513.4662605699486, 'median': 513.2093307500327, 'std': 2.184630412673929}
</pre></div>
</div>
</div>
@@ -752,179 +752,177 @@ 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: 23.66/ 23.66 GFLOPS | Progress: (4/20) | 10.10 s
-[Task 1/25] Current/Best: 15.03/ 23.66 GFLOPS | Progress: (8/20) | 15.25 s
-[Task 1/25] Current/Best: 7.55/ 23.66 GFLOPS | Progress: (12/20) | 18.41 s
-[Task 1/25] Current/Best: 9.44/ 23.66 GFLOPS | Progress: (16/20) | 20.63 s
-[Task 1/25] Current/Best: 14.89/ 23.66 GFLOPS | Progress: (20/20) | 27.44 s Done.
+[Task 1/25] Current/Best: 19.21/ 19.21 GFLOPS | Progress: (4/20) | 10.96 s
+[Task 1/25] Current/Best: 23.77/ 23.77 GFLOPS | Progress: (8/20) | 16.35 s
+[Task 1/25] Current/Best: 12.56/ 23.77 GFLOPS | Progress: (12/20) | 20.03 s
+[Task 1/25] Current/Best: 11.70/ 23.77 GFLOPS | Progress: (16/20) | 22.37 s
+[Task 1/25] Current/Best: 23.79/ 23.79 GFLOPS | Progress: (20/20) | 25.61 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 15.85/ 19.97 GFLOPS | Progress: (4/20) | 4.53 s
-[Task 2/25] Current/Best: 7.86/ 19.97 GFLOPS | Progress: (8/20) | 6.78 s
-[Task 2/25] Current/Best: 13.32/ 21.26 GFLOPS | Progress: (12/20) | 8.67 s
-[Task 2/25] Current/Best: 13.22/ 21.26 GFLOPS | Progress: (16/20) | 10.62 s
-[Task 2/25] Current/Best: 13.37/ 21.26 GFLOPS | Progress: (20/20) | 12.55 s Done.
+[Task 2/25] Current/Best: 19.71/ 19.71 GFLOPS | Progress: (4/20) | 4.23 s
+[Task 2/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (8/20) | 5.67 s
+[Task 2/25] Current/Best: 18.64/ 19.99 GFLOPS | Progress: (12/20) | 7.37 s
+[Task 2/25] Current/Best: 11.91/ 19.99 GFLOPS | Progress: (16/20) | 9.30 s
+[Task 2/25] Current/Best: 16.25/ 19.99 GFLOPS | Progress: (20/20) | 11.39 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 5.58/ 17.06 GFLOPS | Progress: (4/20) | 5.61 s
-[Task 3/25] Current/Best: 16.94/ 17.06 GFLOPS | Progress: (8/20) | 8.26 s
-[Task 3/25] Current/Best: 11.57/ 19.07 GFLOPS | Progress: (12/20) | 10.31 s
-[Task 3/25] Current/Best: 14.92/ 22.81 GFLOPS | Progress: (16/20) | 12.56 s
-[Task 3/25] Current/Best: 9.24/ 23.02 GFLOPS | Progress: (20/20) | 14.88 s Done.
+[Task 3/25] Current/Best: 11.24/ 16.20 GFLOPS | Progress: (4/20) | 5.51 s
+[Task 3/25] Current/Best: 9.25/ 16.20 GFLOPS | Progress: (8/20) | 7.90 s
+[Task 3/25] Current/Best: 6.16/ 16.20 GFLOPS | Progress: (12/20) | 10.50 s
+[Task 3/25] Current/Best: 6.20/ 16.20 GFLOPS | Progress: (16/20) | 13.04 s
+[Task 3/25] Current/Best: 5.88/ 20.98 GFLOPS | Progress: (20/20) | 15.74 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 6.67/ 20.16 GFLOPS | Progress: (4/20) | 5.09 s
-[Task 4/25] Current/Best: 16.29/ 20.16 GFLOPS | Progress: (8/20) | 7.29 s
-[Task 4/25] Current/Best: 16.81/ 20.16 GFLOPS | Progress: (12/20) | 11.28 s
-[Task 4/25] Current/Best: 9.52/ 20.16 GFLOPS | Progress: (16/20) | 17.87 s
-[Task 4/25] Current/Best: 7.14/ 20.16 GFLOPS | Progress: (20/20) | 20.10 s Done.
+[Task 4/25] Current/Best: 11.66/ 16.56 GFLOPS | Progress: (4/20) | 6.30 s
+[Task 4/25] Current/Best: 14.76/ 16.56 GFLOPS | Progress: (8/20) | 8.83 s
+[Task 4/25] Current/Best: 12.20/ 16.56 GFLOPS | Progress: (12/20) | 14.01 s
+[Task 4/25] Current/Best: 13.17/ 16.56 GFLOPS | Progress: (16/20) | 17.22 s
+[Task 4/25] Current/Best: 12.73/ 16.56 GFLOPS | Progress: (20/20) | 19.71 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 17.74/ 17.74 GFLOPS | Progress: (4/20) | 5.22 s
-[Task 5/25] Current/Best: 10.56/ 20.50 GFLOPS | Progress: (8/20) | 7.42 s
-[Task 5/25] Current/Best: 17.52/ 20.50 GFLOPS | Progress: (12/20) | 9.41 s
-[Task 5/25] Current/Best: 14.26/ 20.50 GFLOPS | Progress: (16/20) | 11.48 s
-[Task 5/25] Current/Best: 17.57/ 20.50 GFLOPS | Progress: (20/20) | 13.59 s Done.
+[Task 5/25] Current/Best: 12.95/ 19.96 GFLOPS | Progress: (4/20) | 4.48 s
+[Task 5/25] Current/Best: 4.79/ 21.49 GFLOPS | Progress: (8/20) | 7.09 s
+[Task 5/25] Current/Best: 17.69/ 21.49 GFLOPS | Progress: (12/20) | 9.29 s
+[Task 5/25] Current/Best: 20.49/ 21.49 GFLOPS | Progress: (16/20) | 11.50 s
+[Task 5/25] Current/Best: 2.93/ 21.49 GFLOPS | Progress: (20/20) | 13.85 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 8.23/ 17.84 GFLOPS | Progress: (4/20) | 5.13 s
-[Task 6/25] Current/Best: 8.59/ 17.84 GFLOPS | Progress: (8/20) | 10.58 s
-[Task 6/25] Current/Best: 4.96/ 18.11 GFLOPS | Progress: (12/20) | 13.06 s
-[Task 6/25] Current/Best: 13.01/ 20.24 GFLOPS | Progress: (16/20) | 16.54 s
-[Task 6/25] Current/Best: 2.84/ 20.24 GFLOPS | Progress: (20/20) | 21.60 s Done.
+[Task 6/25] Current/Best: 5.73/ 18.60 GFLOPS | Progress: (4/20) | 5.11 s
+[Task 6/25] Current/Best: 18.44/ 18.60 GFLOPS | Progress: (8/20) | 7.38 s
+[Task 6/25] Current/Best: 5.00/ 18.60 GFLOPS | Progress: (12/20) | 10.47 s
+[Task 6/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (16/20) | 13.05 s
+[Task 6/25] Current/Best: 13.82/ 23.23 GFLOPS | Progress: (20/20) | 15.45 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 14.86/ 17.42 GFLOPS | Progress: (4/20) | 5.42 s
-[Task 7/25] Current/Best: 22.81/ 22.81 GFLOPS | Progress: (8/20) | 7.67 s
-[Task 7/25] Current/Best: 15.96/ 22.81 GFLOPS | Progress: (12/20) | 9.75 s
-[Task 7/25] Current/Best: 18.03/ 22.81 GFLOPS | Progress: (16/20) | 12.53 s
-[Task 7/25] Current/Best: 13.44/ 22.81 GFLOPS | Progress: (20/20) | 16.51 s Done.
+[Task 7/25] Current/Best: 15.34/ 20.00 GFLOPS | Progress: (4/20) | 5.10 s
+[Task 7/25] Current/Best: 12.75/ 20.57 GFLOPS | Progress: (8/20) | 7.88 s
+[Task 7/25] Current/Best: 15.66/ 20.57 GFLOPS | Progress: (12/20) | 11.79 s
+[Task 7/25] Current/Best: 14.02/ 20.57 GFLOPS | Progress: (16/20) | 14.05 s
+[Task 7/25] Current/Best: 11.04/ 20.57 GFLOPS | Progress: (20/20) | 17.33 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 2.76/ 19.54 GFLOPS | Progress: (4/20) | 5.68 s
-[Task 8/25] Current/Best: 6.03/ 19.54 GFLOPS | Progress: (8/20) | 15.19 s
-[Task 8/25] Current/Best: 13.90/ 19.54 GFLOPS | Progress: (12/20) | 20.26 s
-[Task 8/25] Current/Best: 4.94/ 19.54 GFLOPS | Progress: (16/20) | 31.99 s
-[Task 8/25] Current/Best: 9.99/ 19.54 GFLOPS | Progress: (20/20) | 35.50 s
+[Task 8/25] Current/Best: 14.18/ 14.18 GFLOPS | Progress: (4/20) | 12.62 s
+[Task 8/25] Current/Best: 5.31/ 20.60 GFLOPS | Progress: (8/20) | 19.13 s
+[Task 8/25] Current/Best: 14.11/ 20.60 GFLOPS | Progress: (12/20) | 26.36 s
+[Task 8/25] Current/Best: 5.89/ 20.60 GFLOPS | Progress: (16/20) | 37.21 s
+[Task 8/25] Current/Best: 13.04/ 20.60 GFLOPS | Progress: (20/20) | 40.32 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 13.78/ 20.35 GFLOPS | Progress: (4/20) | 4.38 s
-[Task 9/25] Current/Best: 9.12/ 20.35 GFLOPS | Progress: (8/20) | 8.29 s
-[Task 9/25] Current/Best: 9.94/ 20.35 GFLOPS | Progress: (12/20) | 11.79 s
-[Task 9/25] Current/Best: 8.20/ 21.34 GFLOPS | Progress: (16/20) | 13.82 s
-[Task 9/25] Current/Best: 20.23/ 21.34 GFLOPS | Progress: (20/20) | 15.55 s Done.
+[Task 9/25] Current/Best: 5.92/ 16.34 GFLOPS | Progress: (4/20) | 4.86 s
+[Task 9/25] Current/Best: 11.67/ 16.96 GFLOPS | Progress: (8/20) | 11.29 s
+[Task 9/25] Current/Best: 8.14/ 21.90 GFLOPS | Progress: (12/20) | 18.62 s
+[Task 9/25] Current/Best: 14.17/ 21.90 GFLOPS | Progress: (16/20) | 24.53 s
+[Task 9/25] Current/Best: 13.94/ 23.04 GFLOPS | Progress: (20/20) | 27.52 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 14.74/ 16.11 GFLOPS | Progress: (4/20) | 4.81 s
-[Task 10/25] Current/Best: 6.98/ 16.11 GFLOPS | Progress: (8/20) | 8.33 s
-[Task 10/25] Current/Best: 5.36/ 16.11 GFLOPS | Progress: (12/20) | 10.91 s
-[Task 10/25] Current/Best: 16.51/ 16.51 GFLOPS | Progress: (16/20) | 12.68 s
-[Task 10/25] Current/Best: 21.93/ 21.93 GFLOPS | Progress: (20/20) | 16.12 s Done.
+[Task 10/25] Current/Best: 16.59/ 18.26 GFLOPS | Progress: (4/20) | 4.90 s
+[Task 10/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (8/20) | 7.36 s
+[Task 10/25] Current/Best: 18.63/ 20.56 GFLOPS | Progress: (12/20) | 10.84 s
+[Task 10/25] Current/Best: 5.25/ 20.56 GFLOPS | Progress: (16/20) | 12.74 s
+[Task 10/25] Current/Best: 12.22/ 20.56 GFLOPS | Progress: (20/20) | 16.44 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 6.23/ 15.92 GFLOPS | Progress: (4/20) | 6.63 s
-[Task 11/25] Current/Best: 15.03/ 15.92 GFLOPS | Progress: (8/20) | 10.02 s
-[Task 11/25] Current/Best: 6.15/ 20.41 GFLOPS | Progress: (12/20) | 12.68 s
-[Task 11/25] Current/Best: 18.68/ 21.84 GFLOPS | Progress: (16/20) | 15.43 s
-[Task 11/25] Current/Best: 11.94/ 21.84 GFLOPS | Progress: (20/20) | 18.23 s Done.
+[Task 11/25] Current/Best: 8.00/ 17.59 GFLOPS | Progress: (4/20) | 6.07 s
+[Task 11/25] Current/Best: 6.27/ 17.59 GFLOPS | Progress: (8/20) | 9.29 s
+[Task 11/25] Current/Best: 13.52/ 17.59 GFLOPS | Progress: (12/20) | 12.25 s
+[Task 11/25] Current/Best: 17.84/ 18.37 GFLOPS | Progress: (16/20) | 16.08 s
+[Task 11/25] Current/Best: 9.41/ 18.37 GFLOPS | Progress: (20/20) | 18.74 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 10.03/ 14.72 GFLOPS | Progress: (4/20) | 5.41 s
-[Task 12/25] Current/Best: 13.90/ 15.52 GFLOPS | Progress: (8/20) | 9.06 s
-[Task 12/25] Current/Best: 2.51/ 16.46 GFLOPS | Progress: (12/20) | 12.00 s
-[Task 12/25] Current/Best: 11.26/ 16.46 GFLOPS | Progress: (16/20) | 15.55 s
-[Task 12/25] Current/Best: 5.93/ 17.46 GFLOPS | Progress: (20/20) | 18.02 s Done.
+[Task 12/25] Current/Best: 8.21/ 17.86 GFLOPS | Progress: (4/20) | 5.29 s
+[Task 12/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (8/20) | 7.51 s
+[Task 12/25] Current/Best: 4.59/ 21.19 GFLOPS | Progress: (12/20) | 9.82 s
+[Task 12/25] Current/Best: 9.66/ 21.19 GFLOPS | Progress: (16/20) | 13.18 s
+[Task 12/25] Current/Best: 5.35/ 21.19 GFLOPS | Progress: (20/20) | 15.57 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 10.37/ 18.55 GFLOPS | Progress: (4/20) | 5.50 s
-[Task 13/25] Current/Best: 9.45/ 18.55 GFLOPS | Progress: (8/20) | 8.44 s
-[Task 13/25] Current/Best: 12.86/ 22.27 GFLOPS | Progress: (12/20) | 11.22 s
-[Task 13/25] Current/Best: 9.08/ 22.27 GFLOPS | Progress: (16/20) | 14.80 s
-[Task 13/25] Current/Best: 20.75/ 22.27 GFLOPS | Progress: (20/20) | 17.46 s Done.
+[Task 13/25] Current/Best: 3.09/ 11.81 GFLOPS | Progress: (4/20) | 6.98 s
+[Task 13/25] Current/Best: 16.15/ 16.15 GFLOPS | Progress: (8/20) | 10.05 s
+[Task 13/25] Current/Best: 5.82/ 16.15 GFLOPS | Progress: (12/20) | 15.67 s
+[Task 13/25] Current/Best: 11.99/ 16.15 GFLOPS | Progress: (16/20) | 20.31 s
+[Task 13/25] Current/Best: 13.23/ 19.65 GFLOPS | Progress: (20/20) | 23.11 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 18.49/ 18.49 GFLOPS | Progress: (4/20) | 6.86 s
-[Task 14/25] Current/Best: 4.74/ 18.49 GFLOPS | Progress: (8/20) | 9.27 s
-[Task 14/25] Current/Best: 12.13/ 18.49 GFLOPS | Progress: (12/20) | 12.74 s
-[Task 14/25] Current/Best: 10.95/ 18.82 GFLOPS | Progress: (16/20) | 16.55 s
-[Task 14/25] Current/Best: 13.36/ 18.82 GFLOPS | Progress: (20/20) | 20.89 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 15/25] Current/Best: 6.18/ 18.22 GFLOPS | Progress: (4/20) | 5.67 s
-[Task 15/25] Current/Best: 21.08/ 21.37 GFLOPS | Progress: (8/20) | 8.13 s
-[Task 15/25] Current/Best: 18.90/ 21.37 GFLOPS | Progress: (12/20) | 11.46 s
-[Task 15/25] Current/Best: 12.46/ 21.37 GFLOPS | Progress: (16/20) | 14.51 s
-[Task 15/25] Current/Best: 16.33/ 21.37 GFLOPS | Progress: (20/20) | 18.91 s
+[Task 14/25] Current/Best: 4.73/ 14.88 GFLOPS | Progress: (4/20) | 5.75 s
+[Task 14/25] Current/Best: 7.48/ 16.14 GFLOPS | Progress: (8/20) | 7.85 s
+[Task 14/25] Current/Best: 10.75/ 16.14 GFLOPS | Progress: (12/20) | 14.18 s
+[Task 14/25] Current/Best: 14.37/ 16.14 GFLOPS | Progress: (16/20) | 16.05 s
+[Task 14/25] Current/Best: 12.96/ 16.14 GFLOPS | Progress: (20/20) | 24.31 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 15/25] Current/Best: 10.30/ 10.30 GFLOPS | Progress: (4/20) | 5.98 s Done.
+
+[Task 15/25] Current/Best: 3.15/ 15.67 GFLOPS | Progress: (8/20) | 9.64 s
+[Task 15/25] Current/Best: 19.62/ 19.62 GFLOPS | Progress: (12/20) | 11.25 s
+[Task 15/25] Current/Best: 19.84/ 21.13 GFLOPS | Progress: (16/20) | 16.03 s
+[Task 15/25] Current/Best: 13.80/ 21.13 GFLOPS | Progress: (20/20) | 19.06 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 12.66/ 14.75 GFLOPS | Progress: (4/20) | 6.21 s
-[Task 16/25] Current/Best: 13.81/ 22.75 GFLOPS | Progress: (8/20) | 8.61 s
-[Task 16/25] Current/Best: 18.15/ 22.75 GFLOPS | Progress: (12/20) | 12.17 s
-[Task 16/25] Current/Best: 6.92/ 22.75 GFLOPS | Progress: (16/20) | 15.89 s
-[Task 16/25] Current/Best: 6.99/ 22.75 GFLOPS | Progress: (20/20) | 18.97 s Done.
+[Task 16/25] Current/Best: 19.09/ 19.09 GFLOPS | Progress: (4/20) | 4.56 s
+[Task 16/25] Current/Best: 18.94/ 19.09 GFLOPS | Progress: (8/20) | 6.10 s
+[Task 16/25] Current/Best: 15.98/ 21.71 GFLOPS | Progress: (12/20) | 8.59 s
+[Task 16/25] Current/Best: 9.31/ 21.71 GFLOPS | Progress: (16/20) | 13.10 s
+[Task 16/25] Current/Best: 10.41/ 21.71 GFLOPS | Progress: (20/20) | 16.39 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 19.51/ 19.51 GFLOPS | Progress: (4/20) | 5.00 s
-[Task 17/25] Current/Best: 12.22/ 22.40 GFLOPS | Progress: (8/20) | 7.95 s
-[Task 17/25] Current/Best: 6.26/ 22.40 GFLOPS | Progress: (12/20) | 10.59 s
-[Task 17/25] Current/Best: 13.73/ 22.40 GFLOPS | Progress: (16/20) | 13.71 s
-[Task 17/25] Current/Best: 6.22/ 22.40 GFLOPS | Progress: (20/20) | 16.16 s Done.
+[Task 17/25] Current/Best: 12.16/ 12.39 GFLOPS | Progress: (4/20) | 5.79 s
+[Task 17/25] Current/Best: 11.78/ 12.39 GFLOPS | Progress: (8/20) | 8.78 s
+[Task 17/25] Current/Best: 3.08/ 23.59 GFLOPS | Progress: (12/20) | 12.64 s
+[Task 17/25] Current/Best: 21.79/ 23.59 GFLOPS | Progress: (16/20) | 16.49 s
+[Task 17/25] Current/Best: 11.82/ 23.59 GFLOPS | Progress: (20/20) | 19.12 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/20) | 4.73 s
-[Task 18/25] Current/Best: 11.80/ 18.14 GFLOPS | Progress: (8/20) | 12.51 s
-[Task 18/25] Current/Best: 6.06/ 18.14 GFLOPS | Progress: (12/20) | 15.25 s
-[Task 18/25] Current/Best: 17.06/ 23.20 GFLOPS | Progress: (16/20) | 18.94 s
-[Task 18/25] Current/Best: 12.07/ 23.20 GFLOPS | Progress: (20/20) | 22.10 s Done.
+[Task 18/25] Current/Best: 7.21/ 14.72 GFLOPS | Progress: (4/20) | 6.35 s
+[Task 18/25] Current/Best: 9.76/ 20.70 GFLOPS | Progress: (8/20) | 10.10 s
+[Task 18/25] Current/Best: 15.49/ 20.70 GFLOPS | Progress: (12/20) | 14.76 s
+[Task 18/25] Current/Best: 7.14/ 20.70 GFLOPS | Progress: (16/20) | 17.57 s
+[Task 18/25] Current/Best: 21.18/ 21.80 GFLOPS | Progress: (20/20) | 19.58 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 10.11/ 20.28 GFLOPS | Progress: (4/20) | 6.17 s
-[Task 19/25] Current/Best: 18.42/ 20.28 GFLOPS | Progress: (8/20) | 8.92 s
-[Task 19/25] Current/Best: 19.55/ 20.70 GFLOPS | Progress: (12/20) | 12.48 s
-[Task 19/25] Current/Best: 9.75/ 21.38 GFLOPS | Progress: (16/20) | 15.90 s
-[Task 19/25] Current/Best: 12.38/ 21.38 GFLOPS | Progress: (20/20) | 18.18 s Done.
+[Task 19/25] Current/Best: 1.56/ 18.73 GFLOPS | Progress: (4/20) | 6.81 s
+[Task 19/25] Current/Best: 10.42/ 20.82 GFLOPS | Progress: (8/20) | 9.81 s
+[Task 19/25] Current/Best: 3.09/ 20.82 GFLOPS | Progress: (12/20) | 14.87 s
+[Task 19/25] Current/Best: 11.53/ 20.82 GFLOPS | Progress: (16/20) | 18.98 s
+[Task 19/25] Current/Best: 10.38/ 20.82 GFLOPS | Progress: (20/20) | 23.74 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 12.82/ 12.82 GFLOPS | Progress: (4/20) | 5.78 s
-[Task 20/25] Current/Best: 18.11/ 18.11 GFLOPS | Progress: (8/20) | 7.63 s
-[Task 20/25] Current/Best: 14.58/ 18.11 GFLOPS | Progress: (12/20) | 11.14 s
-[Task 20/25] Current/Best: 13.30/ 18.11 GFLOPS | Progress: (16/20) | 13.51 s
-[Task 20/25] Current/Best: 17.06/ 18.11 GFLOPS | Progress: (20/20) | 16.95 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 21/25] Current/Best: 5.41/ 18.29 GFLOPS | Progress: (4/20) | 6.23 s
-[Task 21/25] Current/Best: 8.87/ 18.29 GFLOPS | Progress: (8/20) | 8.73 s
-[Task 21/25] Current/Best: 4.49/ 22.96 GFLOPS | Progress: (12/20) | 11.86 s
-[Task 21/25] Current/Best: 23.09/ 23.09 GFLOPS | Progress: (16/20) | 13.51 s
-[Task 21/25] Current/Best: 8.87/ 23.09 GFLOPS | Progress: (20/20) | 15.19 s
+[Task 20/25] Current/Best: 14.78/ 15.35 GFLOPS | Progress: (4/20) | 5.30 s
+[Task 20/25] Current/Best: 15.51/ 15.51 GFLOPS | Progress: (8/20) | 7.62 s
+[Task 20/25] Current/Best: 7.46/ 15.51 GFLOPS | Progress: (12/20) | 11.49 s
+[Task 20/25] Current/Best: 7.22/ 19.22 GFLOPS | Progress: (16/20) | 14.49 s
+[Task 20/25] Current/Best: 6.84/ 19.22 GFLOPS | Progress: (20/20) | 17.51 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 21/25] Current/Best: 18.80/ 18.80 GFLOPS | Progress: (4/20) | 5.93 s Done.
+
+[Task 21/25] Current/Best: 9.30/ 18.80 GFLOPS | Progress: (8/20) | 8.85 s
+[Task 21/25] Current/Best: 22.04/ 22.04 GFLOPS | Progress: (12/20) | 11.07 s
+[Task 21/25] Current/Best: 8.40/ 22.04 GFLOPS | Progress: (16/20) | 16.63 s
+[Task 21/25] Current/Best: 8.66/ 22.04 GFLOPS | Progress: (20/20) | 18.72 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 10.85/ 18.96 GFLOPS | Progress: (4/20) | 5.94 s
-[Task 22/25] Current/Best: 5.06/ 18.96 GFLOPS | Progress: (8/20) | 8.65 s
-[Task 22/25] Current/Best: 10.36/ 18.96 GFLOPS | Progress: (12/20) | 12.47 s
-[Task 22/25] Current/Best: 4.22/ 18.99 GFLOPS | Progress: (16/20) | 15.23 s
-[Task 22/25] Current/Best: 15.64/ 18.99 GFLOPS | Progress: (20/20) | 17.19 s Done.
+[Task 22/25] Current/Best: 18.07/ 19.52 GFLOPS | Progress: (4/20) | 5.83 s
+[Task 22/25] Current/Best: 12.88/ 19.52 GFLOPS | Progress: (8/20) | 8.58 s
+[Task 22/25] Current/Best: 2.76/ 19.52 GFLOPS | Progress: (12/20) | 10.54 s
+[Task 22/25] Current/Best: 5.15/ 19.52 GFLOPS | Progress: (16/20) | 12.32 s
+[Task 22/25] Current/Best: 10.31/ 19.62 GFLOPS | Progress: (20/20) | 14.96 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 2.72/ 12.40 GFLOPS | Progress: (4/20) | 6.27 s
-[Task 23/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (8/20) | 11.98 s
-[Task 23/25] Current/Best: 22.48/ 22.48 GFLOPS | Progress: (12/20) | 14.56 s
-[Task 23/25] Current/Best: 22.35/ 22.58 GFLOPS | Progress: (16/20) | 19.23 s
-[Task 23/25] Current/Best: 6.04/ 22.58 GFLOPS | Progress: (20/20) | 23.17 s Done.
+[Task 23/25] Current/Best: 10.30/ 17.48 GFLOPS | Progress: (4/20) | 5.23 s
+[Task 23/25] Current/Best: 9.65/ 17.48 GFLOPS | Progress: (8/20) | 8.47 s
+[Task 23/25] Current/Best: 17.69/ 17.69 GFLOPS | Progress: (12/20) | 11.98 s
+[Task 23/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (16/20) | 14.76 s
+[Task 23/25] Current/Best: 19.68/ 19.68 GFLOPS | Progress: (20/20) | 17.75 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 4.06/ 7.23 GFLOPS | Progress: (4/20) | 5.71 s
-[Task 24/25] Current/Best: 6.04/ 10.69 GFLOPS | Progress: (8/20) | 16.35 s
-[Task 24/25] Current/Best: 7.85/ 10.69 GFLOPS | Progress: (12/20) | 19.28 s
-[Task 24/25] Current/Best: 2.45/ 10.69 GFLOPS | Progress: (16/20) | 29.94 s
-[Task 24/25] Current/Best: 4.19/ 10.69 GFLOPS | Progress: (20/20) | 33.36 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
-[Task 25/25] Current/Best: 3.04/ 9.83 GFLOPS | Progress: (4/20) | 4.39 s
-[Task 25/25] Current/Best: 6.18/ 9.83 GFLOPS | Progress: (8/20) | 15.30 s
-[Task 25/25] Current/Best: 5.23/ 9.83 GFLOPS | Progress: (12/20) | 18.51 s
-[Task 25/25] Current/Best: 3.09/ 9.83 GFLOPS | Progress: (16/20) | 20.21 s
-[Task 25/25] Current/Best: 6.31/ 9.83 GFLOPS | Progress: (20/20) | 21.93 s
+[Task 24/25] Current/Best: 1.24/ 2.97 GFLOPS | Progress: (4/20) | 13.55 s
+[Task 24/25] Current/Best: 2.86/ 2.97 GFLOPS | Progress: (8/20) | 26.05 s
+[Task 24/25] Current/Best: 6.75/ 6.75 GFLOPS | Progress: (12/20) | 38.46 s
+[Task 24/25] Current/Best: 3.32/ 6.75 GFLOPS | Progress: (16/20) | 49.49 s
+[Task 24/25] Current/Best: 3.43/ 6.75 GFLOPS | Progress: (20/20) | 59.88 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 8.66/ 9.36 GFLOPS | Progress: (4/20) | 15.21 s
+[Task 25/25] Current/Best: 3.01/ 9.36 GFLOPS | Progress: (8/20) | 19.09 s
+[Task 25/25] Current/Best: 3.02/ 9.36 GFLOPS | Progress: (12/20) | 25.08 s
+[Task 25/25] Current/Best: 1.55/ 9.36 GFLOPS | Progress: (16/20) | 36.06 s
+[Task 25/25] Current/Best: 8.57/ 9.36 GFLOPS | Progress: (20/20) | 38.78 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -985,8 +983,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -1023,8 +1021,8 @@ 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': 384.0942227599953, 'median': 384.69915269998864, 'std': 1.9332749642127023}
-unoptimized: {'mean': 516.0434589399995, 'median': 516.7266176999988, 'std': 1.4996019181741262}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 415.24757281997154, 'median': 415.3037009999025, 'std': 0.714092807443414}
+unoptimized: {'mean': 513.4662605699486, 'median': 513.2093307500327, 'std': 2.184630412673929}
</pre></div>
</div>
</div>
@@ -1038,7 +1036,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 3.951 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 13 minutes 8.340 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 2327bcdbb5..c3ec68c759 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>1.265e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.25e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index d030ced49d..9e6d432d27 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, 0xf006a20)), stage(b, placeholder(b, 0x228c8ba0)), 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 [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x248678b0)), stage(b, placeholder(b, 0x174fc9f0)), 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 [...]
</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 4518a1db3c..c3b7a4fe95 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>15:57.819</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>16:49.567</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>12:03.951</p></td>
+<td><p>13:08.340</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:33.151</p></td>
+<td><p>01:31.405</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>00:58.231</p></td>
+<td><p>00:59.612</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:42.786</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
+<td><p>00:38.012</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:36.884</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
+<td><p>00:30.411</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>00:01.791</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.879</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>00:00.857</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.731</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>00:00.168</p></td>
+<td><p>00:00.178</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 41d31f8958..f5b0c96b89 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -555,7 +555,7 @@ helper function to run a profile of the TVM generated code.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
-naive: 0.000009
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -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: 0.000006
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
</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: 0.000041
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000040
# 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 6.527969999297056e-06 1.0
- naive 9.4609e-06 1.449286684990704
-parallel 5.8872e-06 0.9018423798874604
- vector 4.08989e-05 6.265178915406178
+ numpy 7.413980019919109e-06 1.0
+ naive 6.860900000000001e-06 0.9254003897457034
+parallel 7.2788000000000005e-06 0.9817668756112209
+ vector 4.04225e-05 5.452199748501755
</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: 0.015286
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018400
</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: 3.275038
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.247699
</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: 0.290459
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.310820
</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: 0.326114
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.337981
# 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: 0.112610
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.120136
# 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: 0.105976
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.110148
# 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: 0.098557
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111110
# 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: 0.130337
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.144702
# 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 3.2750378463000005 1.0
- blocking 0.290458601 0.08868862426373113
- vectorization 0.3261143877 0.09957576156514658
-loop permutation 0.1126095973 0.034384212514436
- array packing 0.10597573580000001 0.03235862935743687
- block caching 0.09855674519999999 0.0300933148944661
- parallelization 0.1303365715 0.039796966513608006
+ none 3.2476994102 1.0
+ blocking 0.3108197049 0.09570457903949278
+ vectorization 0.3379811444 0.10406786519051232
+loop permutation 0.12013553810000002 0.03699096588886649
+ array packing 0.1101475325 0.03391555639480099
+ block caching 0.11111027440000001 0.034211994512496346
+ parallelization 0.14470213699999998 0.044555273971949555
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a