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 2023/02/22 19:41:01 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@5f610f45a0bd57eb8a0d8a953d0a0d3b7e0a61b1)
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 cfda5b3647 deploying docs (apache/tvm@5f610f45a0bd57eb8a0d8a953d0a0d3b7e0a61b1)
cfda5b3647 is described below
commit cfda5b36472a4dc7a11078c8941db6bdba19ae90
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Feb 22 19:40:54 2023 +0000
deploying docs (apache/tvm@5f610f45a0bd57eb8a0d8a953d0a0d3b7e0a61b1)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 344888 -> 363056 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 24077 -> 25077 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 696 ++++++++++++++++++---
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 139 ++--
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 329 +++++-----
.../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 | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../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 | 6 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 16 +-
docs/how_to/compile_models/from_pytorch.html | 15 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 53 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 696 ++++++++++++++++++---
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 139 ++--
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 329 +++++-----
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 16 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/install/nnpack.html | 12 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 ++--
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 5 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 270 ++++----
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
128 files changed, 2502 insertions(+), 1471 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 03eff51625..9cef206287 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 ce827177eb..864c62f272 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 29c6c2c451..e692a0e26d 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 21.209 seconds)
+ **Total running time of the script:** ( 1 minutes 18.654 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 2a4a4e5aca..9705b23dc4 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 943ms/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 946ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 4f95cb1f69..891c369dd6 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.zipb601c6c4-6735-41f2-9121-ddff7bc186d1 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip777d6483-6f95-4182-8756-6db7e5dd03f7 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 aeea2a5ded..fd7e83e32f 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, 57.6MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 43.8MB/s]
45%|####4 | 18.6M/41.5M [00:00<00:00, 33.8MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 30.9MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 33.1MB/s]
85%|########4 | 35.2M/41.5M [00:01<00:00, 29.4MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 24.9MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 30.6MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 42.2MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 46.7MB/s]
46%|####5 | 18.9M/41.5M [00:00<00:00, 41.9MB/s]
55%|#####5 | 22.9M/41.5M [00:00<00:00, 37.5MB/s]
64%|######3 | 26.5M/41.5M [00:00<00:00, 37.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 43.0MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 43.1MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 39.7MB/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 fb3dd5623a..8e4f10a1cc 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]
13%|#3 | 5.84M/44.7M [00:00<00:00, 61.3MB/s]
26%|##6 | 11.7M/44.7M [00:00<00:00, 51.4MB/s]
47%|####7 | 21.2M/44.7M [00:00<00:00, 71.3MB/s]
63%|######3 | 28.2M/44.7M [00:00<00:00, 68.9MB/s]
78%|#######8 | 35.0M/44.7M [00:00<00:00, 66.4MB/s]
93%|#########2| 41.4M/44.7M [00:00<00:00, 62.5MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 62.9MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
14%|#4 | 6.30M/44.7M [00:00<00:00, 51.0MB/s]
30%|##9 | 13.2M/44.7M [00:00<00:00, 61.9MB/s]
43%|####3 | 19.2M/44.7M [00:00<00:00, 62.1MB/s]
56%|#####6 | 25.2M/44.7M [00:00<00:00, 62.2MB/s]
70%|######9 | 31.2M/44.7M [00:00<00:00, 52.7MB/s]
83%|########3 | 37.2M/44.7M [00:00<00:00, 55.8MB/s]
99%|#########8| 44.2M/44.7M [00:00<00:00, 55.7MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 57.1MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index a8eacc55f6..21d72b65ff 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 24.204 seconds)
+ **Total running time of the script:** ( 1 minutes 23.283 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 af511063fa..34fd2e7cc5 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
=================
-**06:36.287** total execution time for **how_to_compile_models** files:
+**06:28.001** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:24.204 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:23.283 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:21.209 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:18.654 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:55.065 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:52.164 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:36.913 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:36.646 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:31.763 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:30.991 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.834 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.942 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.929 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:27.500 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:25.263 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.454 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:21.363 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:20.704 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.742 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.662 | 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 634e71b6ce..025d919ddc 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
@@ -727,7 +727,7 @@ 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)
- 2686.8386 2686.5596 2689.3464 2684.8712 1.3741
+ 2682.4603 2682.0656 2684.9652 2681.1275 1.1873
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 2b3dbf6551..b218d2f2ee 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2502 16.0669 17.0351 15.9991 0.3813
+ 15.7550 15.7885 16.0648 15.4662 0.1803
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 bb97b630e8..d91b6c3954 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]
1%|1 | 2.05M/170M [00:00<00:12, 13.9MB/s]
3%|2 | 4.55M/170M [00:00<00:11, 15.7MB/s]
5%|4 | 7.99M/170M [00:00<00:09, 17.8MB/s]
9%|9 | 16.1M/170M [00:00<00:04, 35.9MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 39.3MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 49.7MB/s]
24%|##3 | 40.0M/170M [00:01<00:02, 54.9MB/s]
28%|##8 | 48.0M/170M [00:01<00:02, 50.5MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 56.0MB/s]
38%|###7 | 64.0M/170M [00:01<00:02, 53.7MB/s]
42%|####2 | 72.0M/170M [00:01<00:02, 51.3MB/s]
48%|####8 | 82.1M/170M [00:01<00:01, 62.5MB/s]
52%|#####2 | 88.6M/170M [00:01<00:01, 52.8MB/s]
56%|#####5 | 94.3M/170M [00:02<00:01, 46.8MB/s]
61%|######1 | 104M/170M [00:02<00:01, 50.8MB/s]
68%|######7 | 115M/170M [00:02<00:00, 64.0MB/s]
72%|#######1 | 122M/170M [00:02<00:00, 56.4MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 51.4MB/s]
80%|######## | 136M/170M [00:02<00:00, 55.7MB/s]
85%|########4 | 144M/170M [00:02<00:00, 58.9MB/s]
89%|########9 | 152M/170M [00:03<00:00, 52.7MB/s]
93%|#########2| 157M/170M [00:03<00:00, 51.2MB/s]
96%|#########5| 162M/170M [00:03<00:00, 49.2MB/s]
98%|#########8| 167M/170M [00:03<00:00, 45.7MB/s]
100%|##########| 170M/170M [00:03<00:00, 48.7MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:03, 52.4MB/s]
8%|8 | 14.3M/170M [00:00<00:03, 44.2MB/s]
11%|# | 18.5M/170M [00:00<00:03, 42.2MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 44.3MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 48.8MB/s]
24%|##3 | 40.0M/170M [00:00<00:02, 55.4MB/s]
28%|##8 | 48.0M/170M [00:00<00:02, 59.4MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 59.3MB/s]
38%|###7 | 64.0M/170M [00:01<00:01, 56.9MB/s]
43%|####2 | 72.7M/170M [00:01<00:01, 65.3MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 60.7MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 59.3MB/s]
56%|#####5 | 94.3M/170M [00:01<00:01, 43.5MB/s]
60%|###### | 102M/170M [00:02<00:01, 50.7MB/s]
64%|######3 | 108M/170M [00:02<00:01, 50.5MB/s]
67%|######6 | 113M/170M [00:02<00:01, 46.2MB/s]
71%|#######1 | 121M/170M [00:02<00:00, 53.8MB/s]
75%|#######5 | 128M/170M [00:02<00:00, 50.7MB/s]
78%|#######8 | 133M/170M [00:02<00:00, 49.3MB/s]
81%|########1 | 138M/170M [00:02<00:00, 38.5MB/s]
85%|########4 | 144M/170M [00:03<00:00, 41.3MB/s]
89%|########9 | 152M/170M [00:03<00:00, 48.5MB/s]
93%|#########3| 158M/170M [00:03<00:00, 41.5MB/s]
96%|#########5| 163M/170M [00:03<00:00, 42.3MB/s]
98%|#########8| 167M/170M [00:03<00:00, 41.6MB/s]
100%|##########| 170M/170M [00:03<00:00, 49.0MB/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 37.503 seconds)
+ **Total running time of the script:** ( 3 minutes 28.185 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 fd9ced13db..734fe3ce26 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, 79.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 107MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 52.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 69.2MB/s]
@@ -409,7 +409,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.7380 90.6503 94.9799 90.0971 0.5665
+ 90.2238 90.1525 91.7630 89.9451 0.2524
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.721 seconds)
+ **Total running time of the script:** ( 1 minutes 13.629 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 ee99d21172..798de30f8c 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)
- 121.5896 121.4800 124.8701 120.7038 0.5781
+ 119.9972 119.9753 122.4845 119.1450 0.4230
@@ -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 28.812 seconds)
+ **Total running time of the script:** ( 2 minutes 27.874 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 f7951f986a..355504b960 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 44.807 seconds)
+ **Total running time of the script:** ( 1 minutes 45.632 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 3d1e1b5f8f..80e48c60d8 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%|5 | 7089/132723 [00:00<00:01, 70878.41KB/s]
12%|#1 | 15621/132723 [00:00<00:01, 79365.25KB/s]
18%|#7 | 23558/132723 [00:00<00:01, 66153.21KB/s]
24%|##4 | 32181/132723 [00:00<00:01, 73220.56KB/s]
30%|##9 | 39721/132723 [00:00<00:01, 62616.44KB/s]
37%|###6 | 48491/132723 [00:00<00:01, 69843.82KB/s]
43%|####3 | 57152/132723 [00:00<00:01, 74728.71KB/s]
49%|####8 | 64916/132723 [00:00<00:00, 72665.03KB/s]
55%|#####4 | 72858/132723 [00:01<00:00, 74605.99KB/s]
61%|######1 | 81541/132723 [00:01<00:00, 78163.13KB/s]
67%|######7 | 89486/132723 [00:01<00:00, 68414.73KB/s]
74%|#######3 | 98207/132723 [00:01<00:00, 73444.61KB/s]
80%|######## | 106832/132723 [00:01<00:00, 76983.08KB/s]
86%|########6 | 114752/132723 [00:01<00:00, 66577.33KB/s]
93%|#########3| 123463/132723 [00:01<00:00, 71866.69KB/s]
100%|########
#9| 132236/132723 [00:01<00:00, 76133.22KB/s]
100%|##########| 132723/132723 [00:01<00:00, 72585.43KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6452/132723 [00:00<00:01, 64511.45KB/s]
11%|#1 | 15045/132723 [00:00<00:01, 77104.98KB/s]
17%|#7 | 22756/132723 [00:00<00:01, 71610.02KB/s]
24%|##3 | 31210/132723 [00:00<00:01, 76481.23KB/s]
29%|##9 | 38907/132723 [00:00<00:01, 75618.99KB/s]
36%|###5 | 47428/132723 [00:00<00:01, 78784.74KB/s]
42%|####2 | 55952/132723 [00:00<00:00, 80852.21KB/s]
49%|####8 | 64453/132723 [00:00<00:00, 82155.76KB/s]
55%|#####4 | 72944/132723 [00:00<00:00, 83006.09KB/s]
61%|######1 | 81496/132723 [00:01<00:00, 83774.11KB/s]
68%|######7 | 89883/132723 [00:01<00:00, 60149.44KB/s]
74%|#######4 | 98288/132723 [00:01<00:00, 60774.88KB/s]
80%|######## | 106298/132723 [00:01<00:00, 65389.12KB/s]
86%|########6 | 114680/132723 [00:01<00:00, 60998.00KB/s]
92%|#########2| 122698/132723 [00:01<00:00, 65606.81KB/s]
99%|########
#8| 131313/132723 [00:01<00:00, 70855.36KB/s]
100%|##########| 132723/132723 [00:01<00:00, 71272.32KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 49.837 seconds)
+ **Total running time of the script:** ( 3 minutes 44.598 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 07979ac1ac..f8955cbdd6 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**15:30.774** total execution time for **how_to_deploy_models** files:
+**15:09.256** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:49.837 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:44.598 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:37.503 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:28.185 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:28.812 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:27.874 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:44.807 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:45.632 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:16.721 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:13.629 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:56.037 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.372 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:42.102 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:40.422 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.633 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.002 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:27.317 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.535 | 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 0a50f62543..f2856190df 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.zipdcc918c2-ce94-4500-85b6-fb8331ff65cd from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb7f38c14-2af6-4ab5-8353-12dcb164a542 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 118192d69b..a85eabc63d 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
=================
-**00:54.759** total execution time for **how_to_extend_tvm** files:
+**00:55.128** 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``) | 00:50.841 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:51.153 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.804 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.839 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.105 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.128 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 4039fc9a03..d5a5b0b7c5 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: 23087us [23087us] (49.26%; 49.26%)
- FoldScaleAxis: 23782us [9us] (50.74%; 50.74%)
- FoldConstant: 23773us [1742us] (50.72%; 99.96%)
- InferType: 22032us [22032us] (47.01%; 92.67%)
+ InferType: 22868us [22868us] (48.95%; 48.95%)
+ FoldScaleAxis: 23848us [9us] (51.05%; 51.05%)
+ FoldConstant: 23838us [1835us] (51.03%; 99.96%)
+ InferType: 22004us [22004us] (47.10%; 92.30%)
@@ -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: 22225us [22225us] (48.40%; 48.40%)
- FoldScaleAxis: 23691us [7us] (51.60%; 51.60%)
- FoldConstant: 23684us [1766us] (51.58%; 99.97%)
- InferType: 21918us [21918us] (47.73%; 92.54%)
+ InferType: 22283us [22283us] (48.34%; 48.34%)
+ FoldScaleAxis: 23817us [7us] (51.66%; 51.66%)
+ FoldConstant: 23810us [1805us] (51.65%; 99.97%)
+ InferType: 22005us [22005us] (47.73%; 92.42%)
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 c391994321..6a7f6ce70e 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: 54.173217 ms
+ Convolution: 42.803230 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 13bad16190..4d8ae61ee0 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
@@ -608,7 +608,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.364560 ms
+ conv2d with tensor core: 13.352287 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 cca2768ce3..6b68fabba5 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: 0.019758
- Baseline: 3.213628
+ Numpy running time: 0.018497
+ Baseline: 3.425754
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.313545
+ Opt1: 0.298768
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.345987
+ Opt2: 0.338181
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117049
+ Opt3: 0.116157
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.109335
+ Opt4: 0.110427
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111237
+ Opt5: 0.113422
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147535
+ Opt6: 0.147519
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 a39a27d8a1..fd23055ca5 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.078** total execution time for **how_to_optimize_operators** files:
+**00:35.164** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.194 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.420 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.683 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.628 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.201 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.116 | 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 89387f7f8b..3432f65803 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:53.878** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:52.818** 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``) | 06:03.017 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:04.984 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:42.731 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:40.201 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:08.967 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:07.959 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:31.119 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:31.997 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.256 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.082 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.788 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.596 | 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 ff9e8e8d9d..af778fcae0 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
@@ -244,44 +244,328 @@ cooperative fetching, unrolling and operator fusion.
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": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 16)
- conv2d_nchw = T.allocate([2], "float32", "local")
- pad_temp_shared = T.allocate([648], "float32", "shared")
- kernel_shared = T.allocate([2304], "float32", "shared")
+ T.launch_thread(blockIdx_x, 32)
+ conv2d_nchw = T.allocate([7], "float32", "local")
+ pad_temp_shared = T.allocate([4032], "float32", "shared")
+ kernel_shared = T.allocate([3072], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 784)
- conv2d_nchw_1 = T.Buffer((1,), data=conv2d_nchw, scope="local", align=4)
+ T.launch_thread(threadIdx_x, 112)
+ conv2d_nchw_1 = T.Buffer((7,), data=conv2d_nchw, scope="local", align=16)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- for rc_outer_outer in range(64):
- cse_var_1: T.int32 = rc_outer_outer * 72
+ conv2d_nchw_1[2] = T.float32(0)
+ conv2d_nchw_1[3] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
+ for rc_outer_outer, ry_outer_outer in T.grid(8, 3):
+ cse_var_4: T.int32 = rc_outer_outer * 3136
+ cse_var_3: T.int32 = rc_outer_outer * 576
+ cse_var_2: T.int32 = ry_outer_outer * 7
+ cse_var_1: T.int32 = ry_outer_outer * 3
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((648,), data=pad_temp_shared, scope="shared")
- with T.launch_thread(threadIdx_x_1, 784):
- if T.likely(threadIdx_x_1 < 648):
- data_1 = T.Buffer((25088,), data=data.data)
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 81 and threadIdx_x_1 % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[rc_outer_outer * 392 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ pad_temp_shared_1 = T.Buffer((4032,), data=pad_temp_shared, scope="shared")
+ data_1 = T.Buffer((25088,), data=data.data)
+ with T.launch_thread(threadIdx_x_1, 112):
+ pad_temp_shared_1[threadIdx_x_1 * 16] = T.if_then_else(1 <= threadIdx_x_1 * 16 % 63 // 9 + ry_outer_outer and threadIdx_x_1 * 16 % 63 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 7 % 9 and threadIdx_x_1 * 7 % 9 < 8, data_1[cse_var_4 + threadIdx_x_1 * 16 // 9 * 7 + cse_var_2 + threadIdx_x_1 * 7 % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 1) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 1) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 2] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 2) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 2) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 2) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 3) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 3) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 4] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 4) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 4) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 4) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 5] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 5) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 5) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 5) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 6] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 6) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 6) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 6) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 7] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 7) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 7) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 7) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 8] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 8) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 8) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 8) % 9 and (threadIdx_x_1 * 7 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 8) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 9] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 16 // 9 + 1) % 7 and ry_outer_outer + (threadIdx_x_1 * 16 // 9 + 1) % 7 < 8 and 1 <= threadIdx_x_1 * 7 % 9 and threadIdx_x_1 * 7 % 9 < 8, data_1[cse_var_4 + threadIdx_x_1 * 16 // 9 * 7 + cse_var_2 + threadIdx_x_1 * 7 % 9 - 1], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 10] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 10) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 10) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 10) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 11] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 11) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 11) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 11) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 12] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 12) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 12) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 12) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 13] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 13) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 13) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 13) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 14] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 14) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 15] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 15) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 112):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1792] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1792) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1793] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1793) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1794] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 30) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 30) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1794) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1795] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 31) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 31) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1795) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1796] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 32) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 32) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1796) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1797] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 33) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 33) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1797) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1798] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 34) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 34) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1798) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1799] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 8) % 9 and (threadIdx_x_1 * 7 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1799) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1800] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 16 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 16 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 7 % 9 and threadIdx_x_1 * 7 % 9 < 8, data_1[cse_var_4 + threadIdx_x_1 * 16 // 9 * 7 + cse_var_2 + threadIdx_x_1 * 7 % 9 + 1392], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1801] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 37) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 37) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1801) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1802] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 38) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 38) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1802) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1803] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 39) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 39) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1803) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1804] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 40) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 40) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1804) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1805] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 41) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 41) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1805) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1806] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1806) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1807] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1807) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 112):
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3584] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3584) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3585] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3585) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3586] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 58) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 58) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3586) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3587] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 59) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 59) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3587) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3588] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 60) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 60) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3588) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3589] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 61) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 61) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3589) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3590] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 62) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 62) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 8) % 9 and (threadIdx_x_1 * 7 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3590) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 8) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3591] = T.if_then_else(1 <= threadIdx_x_1 * 16 % 63 // 9 + ry_outer_outer and threadIdx_x_1 * 16 % 63 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 7 % 9 and threadIdx_x_1 * 7 % 9 < 8, data_1[cse_var_4 + threadIdx_x_1 * 16 // 9 * 7 + cse_var_2 + threadIdx_x_1 * 7 % 9 + 2785], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3592] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 1) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 1) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3592) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3593] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 2) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 2) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3593) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3594] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 3) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 3) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3594) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3595] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 4) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 4) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3595) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3596] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 5) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 5) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3596) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3597] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 6) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 6) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3597) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3598] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 7) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 7) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3598) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3599] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 8) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 8) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 8) % 9 and (threadIdx_x_1 * 7 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3599) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 8) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((2304,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((3072,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 784):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 72 * 4608 + cse_var_1 + threadIdx_x_2 % 72]
- with T.launch_thread(threadIdx_x_2, 784):
- kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 784) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 72 // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 784):
- if T.likely(threadIdx_x_2 < 736):
- kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 1568) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 56) % 72 // 3 * 3 + (threadIdx_x_2 + 2) % 3]
- for rc_outer_inner, ry_outer_inner in T.grid(8, 3):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 1152]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 1]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 1153]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 2]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 1154]
- compute_1 = T.Buffer((25088,), data=compute.data)
- bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 1568 + threadIdx_x] = T.max(conv2d_nchw_1[0] + bias_1[blockIdx_x * 32 + threadIdx_x // 49], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x + 784] = T.max(conv2d_nchw_1[1] + bias_1[blockIdx_x * 32 + threadIdx_x // 49 + 16], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 112] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 112) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 112) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 224] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 224) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 336) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 48) % 64 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 448] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 448) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 560] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 560) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 176) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 672) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 32) % 64 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 784) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 896] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 896) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 128) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1008] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1008) // 192 * 4608 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 144]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1120] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1120) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 160) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1232] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1232) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1344] = kernel_1[blockIdx_x * 73728 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 32256]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1456] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1456) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 112) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1568) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1680] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1680) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 48) % 64 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1792] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1792) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1904] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1904) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 176) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2016] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2016) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 32) % 64 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2128] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2128) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2240] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2240) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 128) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2352] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2352) // 192 * 4608 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 144]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2464] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2464) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 160) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2576] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2576) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2688] = kernel_1[blockIdx_x * 73728 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 64512]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2800] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2800) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 112) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2912] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2912) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ if T.likely(threadIdx_x_2 < 48):
+ kernel_shared_1[threadIdx_x_2 + 3024] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 3024) // 192 * 4608 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 432]
+ for rc_outer_inner in range(8):
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 144] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 153] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 162] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 171] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 180] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 145] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 154] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 163] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 172] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 181] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 146] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 155] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 164] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 173] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 182] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 198] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 207] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 216] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 225] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 234] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 243] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 199] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 208] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 217] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 226] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 235] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 244] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 200] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 209] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 218] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 227] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 236] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 245] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 261] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 270] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 279] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 288] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 297] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 306] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 262] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 271] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 280] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 289] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 298] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 307] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 263] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 272] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 281] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 290] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 299] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 308] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 324] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 333] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 342] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 351] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 360] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 369] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 325] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 334] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 343] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 352] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 361] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 370] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 326] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 335] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 344] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 353] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 362] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 371] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 387] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 396] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 405] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 414] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 423] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 432] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 388] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 397] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 406] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 415] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 424] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 433] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 389] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 398] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 407] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 416] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 425] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 434] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 450] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 459] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 468] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 477] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 486] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 495] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 451] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 460] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 469] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 478] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 487] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 496] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 452] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 461] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 470] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 479] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 488] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 497] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ for i2_inner in range(7):
+ compute_1 = T.Buffer((25088,), data=compute.data)
+ bias_1 = T.Buffer((512,), data=bias.data)
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i2_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7], T.float32(0))
@@ -331,7 +615,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.325 ms
+ Execution time of this operator: 0.335 ms
@@ -382,19 +666,19 @@ 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=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
- conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=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=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 [...]
@@ -403,9 +687,9 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -428,14 +712,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=784)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=16)
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=784)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -453,36 +737,306 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(784) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[2];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[2304];
+ extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 648) {
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 736) {
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1152)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1153)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1154)]));
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 16)] = (((((1 <= ((((((int)threadIdx.x) * 16) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) * 16) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 2) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 4) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 4) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 5) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 5) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 5) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 6)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 6) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 6) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 6) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 7)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 7) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 8)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 8) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 9)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 16) / 9) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 16) / 9) + 1) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) * 16) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 10)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 10) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 10) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 10) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 11)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 11) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 11) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 11) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 12)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 12) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 12) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 12) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 13)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 13) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 13) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 13) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 14)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 14) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 15)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 15) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1792)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1793)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1793) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1794)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1794) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1795)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1795) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1796)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 32) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 32) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1796) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1797)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 33) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 33) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1797) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1798)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 34) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 34) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1798) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1799)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1799) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1800)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 16) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 16) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) * 16) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 7) % 9)) + 1392)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1801)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 37) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 37) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1801) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1802)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 38) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 38) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1802) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1803)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 39) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 39) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1803) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1804)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 40) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 40) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1804) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1805)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 41) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 41) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1805) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1806)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1806) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1807)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1807) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3584)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3584) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3585)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3585) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3586)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 58) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 58) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3586) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3587)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 59) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 59) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3587) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3588)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 60) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 60) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3588) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3589)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 61) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 61) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3589) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3590)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 62) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 62) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3590) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3591)] = (((((1 <= ((((((int)threadIdx.x) * 16) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) * 16) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 7) % 9)) + 2785)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3592)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3592) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3593)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3593) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3594)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3594) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3595)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 4) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3595) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3596)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 5) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 5) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3596) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3597)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 6) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 6) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3597) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3598)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3598) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3599)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3599) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 48) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 160) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1680) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 48) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1792) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1904) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2016) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2128) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2240) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2464) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 160) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2576) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2800) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2912) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 48) {
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3024) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 432)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
}
}
}
- compute[((((int)blockIdx.x) * 1568) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + ((int)threadIdx.x)) + 784)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 49)) + 16)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ }
}
@@ -541,7 +1095,7 @@ 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 3.017 seconds)
+ **Total running time of the script:** ( 6 minutes 4.984 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 5cbefca100..226404eef8 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)
- 7.9416 7.9379 7.9533 7.9337 0.0084
+ 7.9007 7.8993 7.9091 7.8938 0.0063
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.967 seconds)
+ **Total running time of the script:** ( 1 minutes 7.959 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 1a58b60162..d2b8338993 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)
- 754.5451 754.5061 758.2794 750.8499 3.0332
+ 751.7400 751.7110 753.7671 749.7419 1.6434
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 42.731 seconds)
+ **Total running time of the script:** ( 1 minutes 40.201 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 a89ddc6ce8..2dc4a8fa3b 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
@@ -389,74 +389,75 @@ 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": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.Buffer((1024,), data=compute_1)
- for 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(cse_var_2, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 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)
- 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_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))
+ for i0_outer in T.parallel(2):
+ compute_1 = T.allocate([2048], "float32", "global")
+ for i1_outer in range(16):
+ compute_2 = T.Buffer((2048,), data=compute_1)
+ for nb_j_inner in range(2):
+ for i_inner_init in range(64):
+ 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(cse_var_2, i1_outer * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 64):
+ 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 = i1_outer * 2 + nb_j_inner
+ cse_var_19: T.int32 = i0_outer * 16384 + i_inner * 256
+ cse_var_18: T.int32 = i_inner * 32 + nb_j_inner * 16
+ cse_var_17: T.int32 = cse_var_18 + 9
+ cse_var_16: T.int32 = cse_var_18 + 8
+ cse_var_15: T.int32 = cse_var_18 + 7
+ cse_var_14: T.int32 = cse_var_18 + 6
+ cse_var_13: T.int32 = cse_var_18 + 5
+ cse_var_12: T.int32 = cse_var_18 + 4
+ cse_var_11: T.int32 = cse_var_18 + 3
+ cse_var_10: T.int32 = cse_var_18 + 2
+ cse_var_9: T.int32 = cse_var_18 + 15
+ cse_var_8: T.int32 = cse_var_18 + 14
+ cse_var_7: T.int32 = cse_var_18 + 13
+ cse_var_6: T.int32 = cse_var_18 + 12
+ cse_var_5: T.int32 = cse_var_18 + 11
+ cse_var_4: T.int32 = cse_var_18 + 10
+ cse_var_3: T.int32 = cse_var_18 + 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)
+ compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ for i0_inner in range(64):
+ cse_var_22: T.int32 = i0_outer * 32768 + i0_inner * 512 + i1_outer * 32
+ compute_3 = T.Buffer((65536,), data=compute.data)
+ placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
+ 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))
@@ -506,7 +507,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.774 ms
+ Execution time of this operator: 1.843 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 e1a27c8e0d..fa29ff01f2 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:47.214** total execution time for **how_to_tune_with_autotvm** files:
+**00:39.018** 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``) | 00:47.181 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:38.983 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 a5df1caa19..4adfd2b38f 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -390,7 +390,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10200261
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8562924
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -513,7 +513,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1076591
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5015952
No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -636,8 +636,11 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1269484
- 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, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5473682
+ No: 4 GFLOPS: 3.78/3.78 result: MeasureResult(costs=(0.06130134575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3446884155273438, timestamp=1677093024.1845086) [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5653298
+ No: 5 GFLOPS: 54.52/54.52 result: MeasureResult(costs=(0.004246405,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.205479145050049, timestamp=1677093033.119018) [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6203369
+ No: 6 GFLOPS: 1.17/54.52 result: MeasureResult(costs=(0.19841366575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.517274379730225, timestamp=1677093036.1125317) [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7067931
+ No: 7 GFLOPS: 0.00/54.52 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 +762,9 @@ 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, 4, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4194246
- 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, 1, 8, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6356639
+ No: 8 GFLOPS: 6.94/54.52 result: MeasureResult(costs=(0.0333526725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5584919452667236, timestamp=1677093036.9794106) [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5599505
+ No: 9 GFLOPS: 0.00/54.52 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
@@ -882,26 +886,8 @@ 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, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7373012
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
- TimeoutError
-
- [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8338281
- No: 7 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, 1, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6099109
+ No: 10 GFLOPS: 0.00/54.52 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
@@ -1023,9 +1009,8 @@ 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, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3863343
- No: 8 GFLOPS: 4.26/4.26 result: MeasureResult(costs=(0.05434336075,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.968520164489746, timestamp=1677092167.710194) [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1008886
- No: 9 GFLOPS: 0.00/4.26 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, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6944217
+ No: 11 GFLOPS: 0.00/54.52 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
@@ -1147,11 +1132,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8321796
- No: 10 GFLOPS: 212.32/212.32 result: MeasureResult(costs=(0.0010903599673913044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4794631004333496, timestamp=1677092171.4352517) [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7944290
- No: 11 GFLOPS: 58.66/212.32 result: MeasureResult(costs=(0.00394652673076923,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2472450733184814, timestamp=1677092172.198755) [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7090860
- No: 12 GFLOPS: 24.20/212.32 result: MeasureResult(costs=(0.009564948272727273,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8552525043487549, timestamp=1677092172.9754047) [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5824490
- No: 13 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3574785
+ No: 12 GFLOPS: 0.00/54.52 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
@@ -1273,8 +1255,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,929090
- No: 14 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,602564
+ No: 13 GFLOPS: 290.42/290.42 result: MeasureResult(costs=(0.0007971163834586467,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2988348007202148, timestamp=1677093038.6338923) [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4187068
+ No: 14 GFLOPS: 0.00/290.42 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
@@ -1396,8 +1379,8 @@ 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, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4081975
- No: 15 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8694834
+ No: 15 GFLOPS: 0.00/290.42 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
@@ -1519,8 +1502,8 @@ 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, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5031475
- No: 16 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 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, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7307562
+ No: 16 GFLOPS: 0.00/290.42 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
@@ -1642,8 +1625,8 @@ 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, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,922227
- No: 17 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3199976
+ No: 17 GFLOPS: 0.00/290.42 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
@@ -1765,9 +1748,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1327363
- No: 18 GFLOPS: 4.87/212.32 result: MeasureResult(costs=(0.047576824000000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.651504755020142, timestamp=1677092178.0493603) [('tile_f', [-1, 1, 4, 16]), ('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, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3750515
- No: 19 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5860480
+ No: 18 GFLOPS: 0.00/290.42 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
@@ -1889,160 +1871,131 @@ 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, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3044787
- No: 20 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9890097
+ No: 19 GFLOPS: 38.97/290.42 result: MeasureResult(costs=(0.005941232736842105,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.738960027694702, timestamp=1677093041.6009665) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('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', 512), ('unroll_explicit', 0)],None,2081940
+ No: 20 GFLOPS: 0.00/290.42 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 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
- During handling of the above exception, another exception occurred:
-
- Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
- tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007efdb9eaffa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1621
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
- TVMError:
- ---------------------------------------------------------------
- An error occurred during the execution of TVM.
- For more information, please see: https://tvm.apache.org/docs/errors.html
- ---------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 2, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2032785
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3124430
@@ -2097,9 +2050,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7944290
+ [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4187068
Finish loading 20 records
- Time cost of this operator: 0.000779
+ Time cost of this operator: 0.001220
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 a94345ebeb..70029899aa 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 310.5 98.714 (1, 2, 10, 10, 3) 2 1 [310.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.09 0.982 (1, 6, 10, 10) 1 1 [3.09]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.304 (1, 1, 10, 10, 3) 1 1 [0.955]
- Total_time - 314.545 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.7 98.39 (1, 2, 10, 10, 3) 2 1 [310.7]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 4.124 1.306 (1, 6, 10, 10) 1 1 [4.124]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.304 (1, 1, 10, 10, 3) 1 1 [0.96]
+ Total_time - 315.785 - - - - -
@@ -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 136.4 98.116 (1, 6, 10, 10, 1) 2 1 [136.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.782 1.282 (1, 6, 10, 10) 1 1 [1.782]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.838 0.603 (1, 3, 10, 10, 1) 1 1 [0.838]
- Total_time - 139.019 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.9 97.418 (1, 6, 10, 10, 1) 2 1 [102.9]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.765 1.671 (1, 6, 10, 10) 1 1 [1.765]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.911 (1, 1, 10, 10, 3) 1 1 [0.962]
+ Total_time - 105.627 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 15.324 seconds)
+ **Total running time of the script:** ( 1 minutes 16.343 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 9a56858c77..1dfcafe838 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]
100%|##########| 3.42M/3.42M [00:00<00:00, 50.1MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 112MB/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 15.558 seconds)
+ **Total running time of the script:** ( 1 minutes 14.650 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 90e718731e..1528452f85 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
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp3h4cg_60/images/random'
+ '/tmp/tmpo2jxte13/images/random'
@@ -309,7 +309,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]
+ :alt: [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp3h4cg_60/images/target contains 8144 images
- /tmp/tmp3h4cg_60/images/random contains 5000 images
+ /tmp/tmpo2jxte13/images/target contains 8144 images
+ /tmp/tmpo2jxte13/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2131 - accuracy: 0.9248 - val_loss: 0.1032 - val_accuracy: 0.9660 - 47s/epoch - 144ms/step
+ 328/328 - 47s - loss: 0.1876 - accuracy: 0.9340 - val_loss: 0.1708 - val_accuracy: 0.9407 - 47s/epoch - 145ms/step
Epoch 2/3
- 328/328 - 43s - loss: 0.1025 - accuracy: 0.9623 - val_loss: 0.0837 - val_accuracy: 0.9694 - 43s/epoch - 132ms/step
+ 328/328 - 44s - loss: 0.0904 - accuracy: 0.9660 - val_loss: 0.1150 - val_accuracy: 0.9611 - 44s/epoch - 133ms/step
Epoch 3/3
- 328/328 - 43s - loss: 0.0709 - accuracy: 0.9716 - val_loss: 0.0882 - val_accuracy: 0.9668 - 43s/epoch - 132ms/step
+ 328/328 - 43s - loss: 0.0647 - accuracy: 0.9766 - val_loss: 0.1037 - val_accuracy: 0.9611 - 43s/epoch - 132ms/step
- <keras.callbacks.History object at 0x7f7aef740f10>
+ <keras.callbacks.History object at 0x7f1a8653c4d0>
@@ -861,7 +861,7 @@ 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 55.274 seconds)
+ **Total running time of the script:** ( 4 minutes 51.267 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 64364af78d..eeb08bd8fe 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**07:43.085** total execution time for **how_to_work_with_microtvm** files:
+**07:38.927** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:55.274 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:51.267 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:15.558 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:16.343 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:15.324 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:14.650 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.840 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.745 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.089 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:06.923 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index c70e0c3888..a250e4b322 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
=================
-**00:45.834** total execution time for **how_to_work_with_relay** files:
+**00:45.622** 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``) | 00:33.995 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.558 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.374 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.277 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.459 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.781 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 9d8b8e925a..454f9f7508 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f7995d549e0>
+ <function my_cuda_math_rule at 0x7f191f090680>
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 8564f1e814..348b686969 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
=================
-**00:04.962** total execution time for **how_to_work_with_schedules** files:
+**00:07.422** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.370 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.909 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.197 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.149 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.592 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.576 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.571 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.560 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.118 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.116 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.053 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.052 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.033 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.032 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.028 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.027 | 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 5b9ee4f973..aa2cc9ffa0 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:31.411** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:31.471** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.404 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.464 | 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 c27ce833a1..7f11f89135 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 33.84s!
+ resnet18_v1 inference graph built in 34.13s!
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 da9ccea1a9..7f41fa76c2 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -337,7 +337,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 22.92s!
+ yolov3-tiny inference graph built in 23.03s!
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 9bd124dd33..0d2c260cd9 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
=================
-**01:40.644** total execution time for **topic_vta_tutorials_frontend** files:
+**01:41.295** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.665 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:51.186 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.979 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:50.108 | 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 997579c77c..def83547ce 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
=================
-**00:03.174** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.215** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.694 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.739 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.480 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.476 | 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 13e9fe4369..8c78b6a101 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
=================
-**00:00.798** total execution time for **topic_vta_tutorials** files:
+**00:00.789** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.413 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.410 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.385 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.379 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index d641d7180a..96e38e5a95 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: 95.598 ms
+ Execution time of this operator: 97.372 ms
@@ -416,7 +416,7 @@ resume the status and do more 5 trials.
.. code-block:: none
Resume search:
-
+ *E
@@ -434,7 +434,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.728 seconds)
+ **Total running time of the script:** ( 1 minutes 31.356 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 83ddfa8d1f..67076b7ceb 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: 2.37/2.37 result: MeasureResult(costs=(0.1133659352,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0658187866210938, timestamp=1677090586.4301212) [('tile_y', [-1, 8]), ('tile_x', [-1, 2])],None,13
- No: 2 GFLOPS: 1.95/2.37 result: MeasureResult(costs=(0.137694009,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.444455862045288, timestamp=1677090588.8943553) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
- No: 3 GFLOPS: 2.92/2.92 result: MeasureResult(costs=(0.09204769900000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7327921390533447, timestamp=1677090591.692557) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
- No: 4 GFLOPS: 10.99/10.99 result: MeasureResult(costs=(0.024420770799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6710712909698486, timestamp=1677090593.4052145) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
- No: 5 GFLOPS: 11.71/11.71 result: MeasureResult(costs=(0.0229258542,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6419792175292969, timestamp=1677090594.2327821) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
- No: 6 GFLOPS: 8.53/11.71 result: MeasureResult(costs=(0.031466835400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7346043586730957, timestamp=1677090594.98831) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
- No: 7 GFLOPS: 11.00/11.71 result: MeasureResult(costs=(0.0244026304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7283415794372559, timestamp=1677090596.693982) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
- No: 8 GFLOPS: 1.89/11.71 result: MeasureResult(costs=(0.1423389596,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5096585750579834, timestamp=1677090599.2308238) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 9 GFLOPS: 9.71/11.71 result: MeasureResult(costs=(0.0276583776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.88291335105896, timestamp=1677090600.2276921) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
- No: 10 GFLOPS: 9.22/11.71 result: MeasureResult(costs=(0.029103458199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.674823522567749, timestamp=1677090600.9527621) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 1 GFLOPS: 13.31/13.31 result: MeasureResult(costs=(0.0201727872,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6522362232208252, timestamp=1677091472.3224754) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
+ No: 2 GFLOPS: 9.04/13.31 result: MeasureResult(costs=(0.029683789999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7252194881439209, timestamp=1677091473.0650053) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
+ No: 3 GFLOPS: 9.33/13.31 result: MeasureResult(costs=(0.028760432600000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7017536163330078, timestamp=1677091474.8107634) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 4 GFLOPS: 11.24/13.31 result: MeasureResult(costs=(0.0238799922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6349952220916748, timestamp=1677091475.455273) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
+ No: 5 GFLOPS: 3.91/13.31 result: MeasureResult(costs=(0.0686975356,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3443591594696045, timestamp=1677091476.9354005) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+ No: 6 GFLOPS: 9.40/13.31 result: MeasureResult(costs=(0.028570181,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6913285255432129, timestamp=1677091478.6950269) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+ No: 7 GFLOPS: 3.94/13.31 result: MeasureResult(costs=(0.0681957996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3592090606689453, timestamp=1677091481.1015615) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+ No: 8 GFLOPS: 2.34/13.31 result: MeasureResult(costs=(0.1144797644,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0604121685028076, timestamp=1677091483.1871216) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 9 GFLOPS: 9.95/13.31 result: MeasureResult(costs=(0.0269727044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7323205471038818, timestamp=1677091484.0323374) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
+ No: 10 GFLOPS: 14.38/14.38 result: MeasureResult(costs=(0.018663065200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5849051475524902, timestamp=1677091484.5908012) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 20c13b46bf..520418a538 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': 515.2758335699855, 'median': 515.3482555999744, 'std': 1.2878188221012696}
+ {'mean': 512.0541001199969, 'median': 511.61899980000385, 'std': 1.4801657422214596}
@@ -545,31 +545,29 @@ 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: 12.35/ 14.99 GFLOPS | Progress: (4/20) | 11.41 s
[Task 1/25] Current/Best: 6.44/ 14.99 GFLOPS | Progress: (8/20) | 16.48 s
[Task 1/25] Current/Best: 12.58/ 21.68 GFLOPS | Progress: (12/20) | 19.79 s
[Task 1/25] Current/Best: 12.35/ 22.53 GFLOPS | Progress: (16/20) | 25.69 s
[Task 1/25] Current/Best: 4.26/ 22.53 GFLOPS | Progress: (20/20) | 30.23 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 14.80/ 16.06 GFLOPS | Progress: (4/20) | 4.56 s
[Task 2/25] Current/Best: 13.13/ 17.17 GFLOPS | Progress: (8/20) | 6.59 s
[Task 2/25] Current/Best: 3.62/ 21.60 GFLOPS | Progress: (12/20) | 8.25 s
[Task 2/25] Current/Best: 17.34/ 21.60 GFLOPS | Progress: (16/20) | 9.96 s
[Task 2/25] Current/Best: 11.65/ 21.60 GFLOPS | Progress: (20/20) | 11.68 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 19.37/ 19.37 GFLOPS | Progress: (4/20) | 4.57 s
[Task 3/25] Current/Best: 6.99/ 19.37 GFLOPS | Progress: (8/20) | 6.97 s
[Task 3/25] Current/Best: 17.51/ 19.37 GFLOPS | Progress: (12/20) | 10.01 s
[Task 3/25] Current/Best: 16.70/ 23.22 GFLOPS | Progress: (16/20) | 12.88 s
[Task 3/25] Current/Best: 10.17/ 23.22 GFLOPS | Progress: (20/20) | 15.43 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 13.92/ 17.58 GFLOPS | Progress: (4/20) | 4.64 s
[Task 4/25] Current/Best: 22.05/ 22.05 GFLOPS | Progress: (8/20) | 6.62 s
[Task 4/25] Current/Best: 15.74/ 22.05 GFLOPS | Progress: (12/20) | 13.60 s
[Task 4/25] Current/Best: 14.40/ 22.05 GFLOPS | Progress: (16/20) | 15.85 s
[Task 4/25] Current/Best: 5.28/ 22.05 GFLOPS | Progress: (20/20) | 20.12 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 19.77/ 19.77 GFLOPS | Progress: (4/20) | 4.32 s
[Task 5/25] Current/Best: 3.26/ 19.77 GFLOPS | Progress: (8/20) | 6.78 s
[Task 5/25] Current/Best: 5.97/ 19.77 GFLOPS | Progress: (12/20) | 8.87 s
[Task 5/25] Current/Best: 19.30/ 19.77 GFLOPS | Progress: (16/20) | 10.70 s
[Task 5/25] Current/Best: 3.99/ 19.77 GFLOPS | Progress: (20/20) | 13.13 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 16.33/ 16.33 GFLOPS | Progress: (4/20) | 4.80 s
[Task 6/25] Current/Best: 22.40/ 22.40 GFLOPS | Progress: (8/20) | 7.94 s
[Task 6/25] Current/Best: 12.81/ 22.40 GFLOPS | Progress: (12/20) | 11.79 s
[Task 6/25] Current/Best: 21.75/ 22.40 GFLOPS | Progress: (16/20) | 14.31 s
[Task 6/25] Current/Best: 8.71/ 22.40 GFLOPS | Progress: (20/20) | 21.03 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.84/ 17.35 GFLOPS | Progress: (4/20) | 4.96 s
[Task 7/25] Current/Best: 9.21/ 18.13 GFLOPS | Progress: (8/20) | 7.72 s
[Task 7/25] Current/Best: 3.15/ 18.13 GFLOPS | Progress: (12/20) | 11.13 s
[Task 7/25] Current/Best: 16.75/ 18.13 GFLOPS | Progress: (16/20) | 13.38 s
[Task 7/25] Current/Best: 15.28/ 18.13 GFLOPS | Progress: (20/20) | 17.14 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.89/ 11.89 GFLOPS | Progress: (4/20) | 6.03 s
[Task 8/25] Current/Best: 8.34/ 18.27 GFLOPS | Progress: (8/20) | 9.62 s
[Task 8/25] Current/Best: 17.71/ 18.27 GFLOPS | Progress: (12/20) | 12.19 s
[Task 8/25] Current/Best: 17.72/ 18.27 GFLOPS | Progress: (16/20) | 14.67 s
[Task 8/25] Current/Best: 5.14/ 18.27 GFLOPS | Progress: (20/20) | 17.01 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 12.04/ 22.76 GFLOPS | Progress: (4/20) | 5.41 s
[Task 9/25] Current/Best: 11.45/ 22.76 GFLOPS | Progress: (8/20) | 8.32 s
[Task 9/25] Current/Best: 6.30/ 22.76 GFLOPS | Progress: (12/20) | 19.58 s
[Task 9/25] Current/Best: 12.58/ 22.76 GFLOPS | Progress: (16/20) | 23.64 s
[Task 9/25] Current/Best: 19.47/ 22.76 GFLOPS | Progress: (20/20) | 25.40 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 5.31/ 15.38 GFLOPS | Progress: (4/20) | 4.36 s
[Task 10/25] Current/Best: 9.11/ 15.38 GFLOPS | Progress: (8/20) | 6.71 s
[Task 10/25] Current/Best: 6.18/ 18.24 GFLOPS | Progress: (12/20) | 8.49 s
[Task 10/25] Current/Best: 2.69/ 18.24 GFLOPS | Progress: (16/20) | 10.56 s
[Task 10/25] Current/Best: 19.21/ 19.23 GFLOPS | Progress: (20/20) | 12.42 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 21.27/ 21.27 GFLOPS | Progress: (4/20) | 5.21 s
[Task 11/25] Current/Best: 21.14/ 21.27 GFLOPS | Progress: (8/20) | 7.62 s
[Task 11/25] Current/Best: 14.79/ 21.84 GFLOPS | Progress: (12/20) | 9.59 s
[Task 11/25] Current/Best: 9.33/ 21.84 GFLOPS | Progress: (16/20) | 11.91 s
[Task 11/25] Current/Best: 8.00/ 21.84 GFLOPS | Progress: (20/20) | 14.40 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 18.73/ 18.73 GFLOPS | Progress: (4/20) | 5.30 s
[Task 12/25] Current/Best: 9.04/ 18.73 GFLOPS | Progress: (8/20) | 9.92 s
[Task 12/25] Current/Best: 11.18/ 18.73 GFLOPS | Progress: (12/20) | 15.76 s
[Task 12/25] Current/Best: 6.80/ 18.73 GFLOPS | Progress: (16/20) | 18.12 s
[Task 12/25] Current/Best: 5.81/ 18.93 GFLOPS | Progress: (20/20) | 20.85 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 10.18/ 19.71 GFLOPS | Progress: (4/20) | 4.96 s
[Task 13/25] Current/Best: 18.15/ 19.71 GFLOPS | Progress: (8/20) | 7.65 s
[Task 13/25] Current/Best: 10.01/ 20.72 GFLOPS | Progress: (12/20) | 9.88 s
[Task 13/25] Current/Best: 5.25/ 20.91 GFLOPS | Progress: (16/20) | 13.30 s
[Task 13/25] Current/Best: 8.66/ 20.91 GFLOPS | Progress: (20/20) | 16.88 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.32/ 16.06 GFLOPS | Progress: (4/20) | 4.44 s
[Task 14/25] Current/Best: 10.78/ 16.53 GFLOPS | Progress: (8/20) | 7.87 s
[Task 14/25] Current/Best: 9.55/ 16.53 GFLOPS | Progress: (12/20) | 12.47 s
[Task 14/25] Current/Best: 16.60/ 16.60 GFLOPS | Progress: (16/20) | 14.94 s
[Task 14/25] Current/Best: 13.10/ 19.01 GFLOPS | Progress: (20/20) | 17.15 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 10.10/ 18.27 GFLOPS | Progress: (4/20) | 8.22 s
[Task 15/25] Current/Best: 11.62/ 18.27 GFLOPS | Progress: (8/20) | 12.92 s
[Task 15/25] Current/Best: 10.70/ 18.27 GFLOPS | Progress: (12/20) | 15.67 s
[Task 15/25] Current/Best: 9.47/ 18.27 GFLOPS | Progress: (16/20) | 21.09 s
[Task 15/25] Current/Best: 6.16/ 21.83 GFLOPS | Progress: (20/2
0) | 23.16 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 10.76/ 21.46 GFLOPS | Progress: (4/20) | 5.20 s
[Task 16/25] Current/Best: 4.94/ 21.46 GFLOPS | Progress: (8/20) | 7.18 s
[Task 16/25] Current/Best: 15.88/ 21.46 GFLOPS | Progress: (12/20) | 8.68 s
[Task 16/25] Current/Best: 17.21/ 21.46 GFLOPS | Progress: (16/20) | 10.93 s
[Task 16/25] Current/Best: 4.92/ 21.46 GFLOPS | Progress: (20/20) | 12.98 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 6.14/ 15.87 GFLOPS | Progress: (4/20) | 5.67 s
[Task 17/25] Current/Best: 8.93/ 16.42 GFLOPS | Progress: (8/20) | 8.21 s
[Task 17/25] Current/Best: 21.73/ 21.73 GFLOPS | Progress: (12/20) | 12.55 s
[Task 17/25] Current/Best: 7.63/ 21.73 GFLOPS | Progress: (16/20) | 16.56 s
[Task 17/25] Current/Best: 18.23/ 22.66 GFLOPS | Progress: (20/20) | 18.84 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 12.18/ 12.66 GFLOPS | Progress: (4/20) | 6.27 s
[Task 18/25] Current/Best: 5.07/ 19.48 GFLOPS | Progress: (8/20) | 12.16 s
[Task 18/25] Current/Best: 23.11/ 23.11 GFLOPS | Progress: (12/20) | 14.70 s
[Task 18/25] Current/Best: 19.40/ 23.11 GFLOPS | Progress: (16/20) | 18.63 s
[Task 18/25] Current/Best: 13.82/ 23.11 GFLOPS | Progress: (20/20) | 21.68 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.78/ 11.91 GFLOPS | Progress: (4/20) | 8.06 s
[Task 19/25] Current/Best: 16.22/ 16.22 GFLOPS | Progress: (8/20) | 10.95 s
[Task 19/25] Current/Best: 6.50/ 20.65 GFLOPS | Progress: (12/20) | 14.07 s
[Task 19/25] Current/Best: 10.52/ 20.65 GFLOPS | Progress: (16/20) | 17.43 s
[Task 19/25] Current/Best: 8.81/ 20.65 GFLOPS | Progress: (20/20) | 21.80 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.65/ 18.30 GFLOPS | Progress: (4/20) | 5.59 s Done.
-
[Task 20/25] Current/Best: 13.79/ 18.30 GFLOPS | Progress: (8/20) | 9.33 s
[Task 20/25] Current/Best: 8.82/ 18.30 GFLOPS | Progress: (12/20) | 12.10 s
[Task 20/25] Current/Best: 6.73/ 18.30 GFLOPS | Progress: (16/20) | 15.76 s
[Task 20/25] Current/Best: 14.32/ 18.30 GFLOPS | Progress: (20/20) | 18.22 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 14.74/ 17.01 GFLOPS | Progress: (4/20) | 5.10 s
[Task 21/25] Current/Best: 6.55/ 17.01 GFLOPS | Progress: (8/20) | 7.24 s
[Task 21/25] Current/Best: 5.14/ 17.01 GFLOPS | Progress: (12/20) | 11.32 s
[Task 21/25] Current/Best: 10.54/ 17.01 GFLOPS | Progress: (16/20) | 13.88 s
[Task 21/25] Current/Best: 4.67/ 17.01 GFLOPS | Progress: (20/20) | 16.65 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 23.09/ 23.09 GFLOPS | Progress: (4/20) | 9.78 s
[Task 1/25] Current/Best: 11.76/ 23.09 GFLOPS | Progress: (8/20) | 13.48 s
[Task 1/25] Current/Best: 12.90/ 23.33 GFLOPS | Progress: (12/20) | 16.69 s
[Task 1/25] Current/Best: 10.99/ 23.33 GFLOPS | Progress: (16/20) | 20.76 s
[Task 1/25] Current/Best: 8.60/ 23.33 GFLOPS | Progress: (20/20) | 24.04 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 20.43/ 20.43 GFLOPS | Progress: (4/20) | 4.11 s
[Task 2/25] Current/Best: 12.96/ 20.43 GFLOPS | Progress: (8/20) | 6.44 s
[Task 2/25] Current/Best: 11.60/ 20.43 GFLOPS | Progress: (12/20) | 7.94 s
[Task 2/25] Current/Best: 9.98/ 20.43 GFLOPS | Progress: (16/20) | 9.88 s
[Task 2/25] Current/Best: 6.11/ 20.43 GFLOPS | Progress: (20/20) | 11.63 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 12.40/ 17.10 GFLOPS | Progress: (4/20) | 4.81 s
[Task 3/25] Current/Best: 22.55/ 22.55 GFLOPS | Progress: (8/20) | 6.75 s
[Task 3/25] Current/Best: 17.63/ 22.55 GFLOPS | Progress: (12/20) | 9.04 s
[Task 3/25] Current/Best: 6.98/ 22.55 GFLOPS | Progress: (16/20) | 12.75 s
[Task 3/25] Current/Best: 12.54/ 22.55 GFLOPS | Progress: (20/20) | 15.56 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 20.98/ 20.98 GFLOPS | Progress: (4/20) | 4.67 s
[Task 4/25] Current/Best: 5.08/ 21.83 GFLOPS | Progress: (8/20) | 9.88 s
[Task 4/25] Current/Best: 7.02/ 21.83 GFLOPS | Progress: (12/20) | 11.83 s
[Task 4/25] Current/Best: 6.21/ 21.83 GFLOPS | Progress: (16/20) | 14.27 s
[Task 4/25] Current/Best: 2.08/ 21.83 GFLOPS | Progress: (20/20) | 17.41 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 10.59/ 15.97 GFLOPS | Progress: (4/20) | 4.73 s
[Task 5/25] Current/Best: 15.28/ 15.97 GFLOPS | Progress: (8/20) | 7.03 s
[Task 5/25] Current/Best: 13.04/ 19.04 GFLOPS | Progress: (12/20) | 8.81 s
[Task 5/25] Current/Best: 12.84/ 19.04 GFLOPS | Progress: (16/20) | 11.38 s
[Task 5/25] Current/Best: 12.90/ 22.77 GFLOPS | Progress: (20/20) | 13.57 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 10.06/ 14.91 GFLOPS | Progress: (4/20) | 5.45 s
[Task 6/25] Current/Best: 17.97/ 18.44 GFLOPS | Progress: (8/20) | 7.62 s
[Task 6/25] Current/Best: 14.04/ 18.44 GFLOPS | Progress: (12/20) | 10.73 s
[Task 6/25] Current/Best: 16.02/ 18.44 GFLOPS | Progress: (16/20) | 14.00 s
[Task 6/25] Current/Best: 9.38/ 18.44 GFLOPS | Progress: (20/20) | 17.28 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 8.93/ 15.58 GFLOPS | Progress: (4/20) | 5.01 s
[Task 7/25] Current/Best: 12.71/ 18.95 GFLOPS | Progress: (8/20) | 7.11 s
[Task 7/25] Current/Best: 9.52/ 18.95 GFLOPS | Progress: (12/20) | 9.53 s
[Task 7/25] Current/Best: 13.07/ 18.95 GFLOPS | Progress: (16/20) | 11.72 s
[Task 7/25] Current/Best: 18.18/ 18.95 GFLOPS | Progress: (20/20) | 14.14 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 11.98/ 13.54 GFLOPS | Progress: (4/20) | 5.91 s
[Task 8/25] Current/Best: 10.77/ 19.07 GFLOPS | Progress: (8/20) | 8.21 s
[Task 8/25] Current/Best: 14.32/ 19.07 GFLOPS | Progress: (12/20) | 11.78 s
[Task 8/25] Current/Best: 7.49/ 20.53 GFLOPS | Progress: (16/20) | 15.39 s
[Task 8/25] Current/Best: 18.66/ 20.53 GFLOPS | Progress: (20/20) | 18.22 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 6.47/ 17.99 GFLOPS | Progress: (4/20) | 6.43 s
[Task 9/25] Current/Best: 12.95/ 22.44 GFLOPS | Progress: (8/20) | 8.21 s
[Task 9/25] Current/Best: 5.97/ 22.44 GFLOPS | Progress: (12/20) | 19.46 s
[Task 9/25] Current/Best: 6.55/ 22.44 GFLOPS | Progress: (16/20) | 30.66 s
[Task 9/25] Current/Best: 5.34/ 22.44 GFLOPS | Progress: (20/20) | 33.82 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 13.76/ 14.01 GFLOPS | Progress: (4/20) | 4.44 s
[Task 10/25] Current/Best: 14.29/ 18.13 GFLOPS | Progress: (8/20) | 6.16 s
[Task 10/25] Current/Best: 16.01/ 18.13 GFLOPS | Progress: (12/20) | 7.83 s
[Task 10/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (16/20) | 11.11 s
[Task 10/25] Current/Best: 16.43/ 18.28 GFLOPS | Progress: (20/20) | 13.57 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (4/20) | 6.22 s
[Task 11/25] Current/Best: 13.08/ 19.44 GFLOPS | Progress: (8/20) | 8.85 s
[Task 11/25] Current/Best: 17.50/ 20.51 GFLOPS | Progress: (12/20) | 11.23 s
[Task 11/25] Current/Best: 16.40/ 20.51 GFLOPS | Progress: (16/20) | 14.07 s
[Task 11/25] Current/Best: 10.03/ 20.51 GFLOPS | Progress: (20/20) | 17.04 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 5.20/ 14.34 GFLOPS | Progress: (4/20) | 8.34 s
[Task 12/25] Current/Best: 12.25/ 18.68 GFLOPS | Progress: (8/20) | 10.57 s
[Task 12/25] Current/Best: 15.83/ 18.68 GFLOPS | Progress: (12/20) | 14.68 s
[Task 12/25] Current/Best: 14.91/ 18.68 GFLOPS | Progress: (16/20) | 19.00 s
[Task 12/25] Current/Best: 5.01/ 18.68 GFLOPS | Progress: (20/20) | 21.97 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.83/ 20.26 GFLOPS | Progress: (4/20) | 5.28 s
[Task 13/25] Current/Best: 7.66/ 20.26 GFLOPS | Progress: (8/20) | 9.20 s
[Task 13/25] Current/Best: 16.95/ 20.26 GFLOPS | Progress: (12/20) | 11.46 s
[Task 13/25] Current/Best: 5.89/ 20.26 GFLOPS | Progress: (16/20) | 14.96 s
[Task 13/25] Current/Best: 9.93/ 20.26 GFLOPS | Progress: (20/20) | 17.34 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 4.53/ 8.90 GFLOPS | Progress: (4/20) | 6.16 s
[Task 14/25] Current/Best: 16.69/ 16.69 GFLOPS | Progress: (8/20) | 10.05 s
[Task 14/25] Current/Best: 15.77/ 16.69 GFLOPS | Progress: (12/20) | 12.46 s
[Task 14/25] Current/Best: 10.06/ 16.69 GFLOPS | Progress: (16/20) | 16.70 s
[Task 14/25] Current/Best: 14.59/ 16.69 GFLOPS | Progress: (20/20) | 19.04 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 11.70/ 12.77 GFLOPS | Progress: (4/20) | 8.39 s
[Task 15/25] Current/Best: 12.21/ 20.88 GFLOPS | Progress: (8/20) | 10.21 s
[Task 15/25] Current/Best: 20.64/ 20.88 GFLOPS | Progress: (12/20) | 12.20 s
[Task 15/25] Current/Best: 11.02/ 20.88 GFLOPS | Progress: (16/20) | 16.83 s
[Task 15/25] Current/Best: 13.87/ 20.88 GFLOPS | Progress: (20/
20) | 19.63 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.02/ 19.02 GFLOPS | Progress: (4/20) | 4.34 s
[Task 16/25] Current/Best: 14.77/ 19.02 GFLOPS | Progress: (8/20) | 6.07 s
[Task 16/25] Current/Best: 10.90/ 19.02 GFLOPS | Progress: (12/20) | 7.84 s
[Task 16/25] Current/Best: 13.50/ 19.02 GFLOPS | Progress: (16/20) | 9.41 s
[Task 16/25] Current/Best: 7.25/ 20.38 GFLOPS | Progress: (20/20) | 11.02 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 19.23/ 19.23 GFLOPS | Progress: (4/20) | 5.26 s
[Task 17/25] Current/Best: 12.18/ 20.77 GFLOPS | Progress: (8/20) | 7.29 s
[Task 17/25] Current/Best: 9.29/ 20.77 GFLOPS | Progress: (12/20) | 11.75 s
[Task 17/25] Current/Best: 8.07/ 20.77 GFLOPS | Progress: (16/20) | 14.20 s
[Task 17/25] Current/Best: 11.83/ 20.77 GFLOPS | Progress: (20/20) | 16.57 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.52/ 15.18 GFLOPS | Progress: (4/20) | 6.03 s
[Task 18/25] Current/Best: 10.12/ 16.20 GFLOPS | Progress: (8/20) | 9.90 s
[Task 18/25] Current/Best: 15.59/ 16.20 GFLOPS | Progress: (12/20) | 12.93 s
[Task 18/25] Current/Best: 16.50/ 16.50 GFLOPS | Progress: (16/20) | 14.94 s
[Task 18/25] Current/Best: 13.42/ 16.50 GFLOPS | Progress: (20/20) | 18.13 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.56/ 18.04 GFLOPS | Progress: (4/20) | 6.83 s
[Task 19/25] Current/Best: 8.24/ 18.04 GFLOPS | Progress: (8/20) | 10.89 s
[Task 19/25] Current/Best: 7.08/ 18.04 GFLOPS | Progress: (12/20) | 15.86 s
[Task 19/25] Current/Best: 22.32/ 22.32 GFLOPS | Progress: (16/20) | 19.86 s
[Task 19/25] Current/Best: 6.93/ 22.32 GFLOPS | Progress: (20/20) | 24.45 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 19.68/ 19.68 GFLOPS | Progress: (4/20) | 5.32 s
[Task 20/25] Current/Best: 18.27/ 19.68 GFLOPS | Progress: (8/20) | 8.65 s
[Task 20/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (12/20) | 12.29 s
[Task 20/25] Current/Best: 12.63/ 21.22 GFLOPS | Progress: (16/20) | 14.78 s
[Task 20/25] Current/Best: 10.56/ 21.22 GFLOPS | Progress: (20/20) | 16.84 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 22/25] Current/Best: 16.08/ 16.08 GFLOPS | Progress: (4/20) | 5.22 s
[Task 22/25] Current/Best: 10.30/ 17.25 GFLOPS | Progress: (8/20) | 10.34 s
[Task 22/25] Current/Best: 3.08/ 17.33 GFLOPS | Progress: (12/20) | 12.42 s
[Task 22/25] Current/Best: 9.54/ 17.33 GFLOPS | Progress: (16/20) | 14.56 s
[Task 22/25] Current/Best: 16.10/ 17.33 GFLOPS | Progress: (20/20) | 16.60 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.57/ 12.98 GFLOPS | Progress: (4/20) | 5.26 s
[Task 23/25] Current/Best: 12.82/ 12.98 GFLOPS | Progress: (8/20) | 8.97 s
[Task 23/25] Current/Best: 12.04/ 17.82 GFLOPS | Progress: (12/20) | 14.32 s
[Task 23/25] Current/Best: 18.39/ 21.89 GFLOPS | Progress: (16/20) | 16.85 s
[Task 23/25] Current/Best: 17.76/ 21.89 GFLOPS | Progress: (20/20) | 20.06 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 4.53/ 9.04 GFLOPS | Progress: (4/20) | 13.45 s
[Task 24/25] Current/Best: 3.27/ 9.04 GFLOPS | Progress: (8/20) | 24.11 s
[Task 24/25] Current/Best: 5.69/ 9.04 GFLOPS | Progress: (12/20) | 35.10 s
[Task 24/25] Current/Best: 3.57/ 9.04 GFLOPS | Progress: (16/20) | 46.06 s
[Task 24/25] Current/Best: 9.68/ 9.68 GFLOPS | Progress: (20/20) | 57.01 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 2.87/ 9.30 GFLOPS | Progress: (4/20) | 5.11 s
[Task 25/25] Current/Best: 9.03/ 9.30 GFLOPS | Progress: (8/20) | 6.76 s
[Task 25/25] Current/Best: 7.52/ 9.30 GFLOPS | Progress: (12/20) | 17.73 s
[Task 25/25] Current/Best: 1.55/ 9.30 GFLOPS | Progress: (16/20) | 28.74 s
[Task 25/25] Current/Best: 8.06/ 9.30 GFLOPS | Progress: (20/20) | 33.55 s
+
[Task 21/25] Current/Best: 7.43/ 20.26 GFLOPS | Progress: (4/20) | 5.87 s
[Task 21/25] Current/Best: 6.67/ 20.26 GFLOPS | Progress: (8/20) | 8.93 s
[Task 21/25] Current/Best: 9.89/ 20.26 GFLOPS | Progress: (12/20) | 15.76 s
[Task 21/25] Current/Best: 2.26/ 20.26 GFLOPS | Progress: (16/20) | 18.26 s
[Task 21/25] Current/Best: 5.38/ 20.26 GFLOPS | Progress: (20/20) | 21.50 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 13.21/ 19.74 GFLOPS | Progress: (4/20) | 5.25 s
[Task 22/25] Current/Best: 9.05/ 19.74 GFLOPS | Progress: (8/20) | 7.49 s
[Task 22/25] Current/Best: 10.63/ 19.74 GFLOPS | Progress: (12/20) | 9.99 s
[Task 22/25] Current/Best: 10.57/ 19.74 GFLOPS | Progress: (16/20) | 11.64 s
[Task 22/25] Current/Best: 10.60/ 19.74 GFLOPS | Progress: (20/20) | 13.31 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.46/ 14.39 GFLOPS | Progress: (4/20) | 5.74 s
[Task 23/25] Current/Best: 11.50/ 17.95 GFLOPS | Progress: (8/20) | 8.92 s
[Task 23/25] Current/Best: 10.83/ 17.95 GFLOPS | Progress: (12/20) | 11.39 s
[Task 23/25] Current/Best: 5.26/ 17.95 GFLOPS | Progress: (16/20) | 17.73 s
[Task 23/25] Current/Best: 12.14/ 17.95 GFLOPS | Progress: (20/20) | 20.97 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.73/ 3.73 GFLOPS | Progress: (4/20) | 13.39 s
[Task 24/25] Current/Best: 2.96/ 10.30 GFLOPS | Progress: (8/20) | 21.73 s
[Task 24/25] Current/Best: 3.68/ 10.30 GFLOPS | Progress: (12/20) | 32.67 s
[Task 24/25] Current/Best: 4.95/ 10.30 GFLOPS | Progress: (16/20) | 35.35 s
[Task 24/25] Current/Best: 10.07/ 10.30 GFLOPS | Progress: (20/20) | 38.24 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 5.87/ 5.87 GFLOPS | Progress: (4/20) | 7.09 s
[Task 25/25] Current/Best: 8.44/ 9.36 GFLOPS | Progress: (8/20) | 18.02 s
[Task 25/25] Current/Best: 8.33/ 9.36 GFLOPS | Progress: (12/20) | 28.70 s
[Task 25/25] Current/Best: 1.55/ 9.36 GFLOPS | Progress: (16/20) | 31.27 s
[Task 25/25] Current/Best: 3.03/ 9.36 GFLOPS | Progress: (20
/20) | 32.74 s
@@ -665,8 +663,8 @@ 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
@@ -723,8 +721,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 409.8005634200035, 'median': 409.5368252500066, 'std': 1.0931895077648477}
- unoptimized: {'mean': 515.2758335699855, 'median': 515.3482555999744, 'std': 1.2878188221012696}
+ optimized: {'mean': 422.1741954800041, 'median': 420.3180206499951, 'std': 3.051434370680484}
+ unoptimized: {'mean': 512.0541001199969, 'median': 511.61899980000385, 'std': 1.4801657422214596}
@@ -747,7 +745,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 20.754 seconds)
+ **Total running time of the script:** ( 11 minutes 54.210 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 0e38325404..bc293b8a50 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
- 1.371e-07 secs/op
+ 1.332e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 555e048ddd..929f110807 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -277,7 +277,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x1395f1a0)), stage(b, placeholder(b, 0x1010b1d0)), 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, 0x11a66320)), stage(b, placeholder(b, 0x11ab8d90)), 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 581ab321b9..a6f0a03fd8 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,31 +5,31 @@
Computation times
=================
-**15:40.372** total execution time for **tutorial** files:
+**15:24.129** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:20.754 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:54.210 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:19.728 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:31.356 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.915 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.946 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.999 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.440 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:22.318 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:18.545 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.869 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.619 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.615 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.853 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.172 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.161 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.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 dd5304fdfc..52e27d7494 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -392,7 +392,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000013
@@ -447,7 +447,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000035
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -504,10 +504,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 6.773159993826994e-06 1.0
- naive 6.8217e-06 1.0071665228958486
- parallel 6.961499999999999e-06 1.0278068148906356
- vector 2.4627900000000002e-05 3.6361019114336117
+ numpy 7.371080000666552e-06 1.0
+ naive 7.4293e-06 1.0078984354162732
+ parallel 1.3010499999999999e-05 1.7650737746467933
+ vector 3.4542600000000004e-05 4.68623322455819
@@ -928,7 +928,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019323
+ Numpy running time: 0.017841
@@ -986,7 +986,7 @@ optimizations.
.. code-block:: none
- none: 3.212878
+ none: 3.420906
@@ -1086,7 +1086,7 @@ schedule.
.. code-block:: none
- blocking: 0.320971
+ blocking: 0.292330
@@ -1170,7 +1170,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.347963
+ vectorization: 0.328753
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1236,7 +1236,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116840
+ loop permutation: 0.117951
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1327,7 +1327,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109135
+ array packing: 0.109251
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1410,7 +1410,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111038
+ block caching: 0.110578
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1484,7 +1484,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.144915
+ parallelization: 0.145928
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1554,13 +1554,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.212877511 1.0
- blocking 0.3209708349 0.09990136063422432
- vectorization 0.3479628775 0.10830256563117385
- loop permutation 0.1168403039 0.036366249102236625
- array packing 0.10913453039999998 0.03396784658809857
- block caching 0.11103821089999999 0.034560362329356165
- parallelization 0.14491518390000002 0.04510448450146347
+ none 3.4209055244000006 1.0
+ blocking 0.2923301274 0.08545401950300055
+ vectorization 0.32875337849999997 0.0961012738162831
+ loop permutation 0.1179507608 0.03447939732877821
+ array packing 0.10925069289999997 0.03193619119872118
+ block caching 0.1105783484 0.03232429180264911
+ parallelization 0.14592845110000002 0.04265784309421836
@@ -1600,6 +1600,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 0.946 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 12a477d8b3..223afca923 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-330fe8d17c5f526e38a44e3f52f96f3ba556be2e
+5f610f45a0bd57eb8a0d8a953d0a0d3b7e0a61b1
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 5cc3cbfd62..b07624dd93 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.209 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.654 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index cedf135efa..af50931a9b 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 943ms/step
+1/1 [==============================] - 1s 946ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 42b55c64c2..d6eb1beb01 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -439,7 +439,7 @@
<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.zipb601c6c4-6735-41f2-9121-ddff7bc186d1 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.zip777d6483-6f95-4182-8756-6db7e5dd03f7 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 d8cc0c6ee5..e2800fb39e 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,14 +449,14 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 57.6MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 43.8MB/s]
- 45%|####4 | 18.6M/41.5M [00:00<00:00, 33.8MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 30.9MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 33.1MB/s]
- 85%|########4 | 35.2M/41.5M [00:01<00:00, 29.4MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 24.9MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 30.6MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 42.2MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 46.7MB/s]
+ 46%|####5 | 18.9M/41.5M [00:00<00:00, 41.9MB/s]
+ 55%|#####5 | 22.9M/41.5M [00:00<00:00, 37.5MB/s]
+ 64%|######3 | 26.5M/41.5M [00:00<00:00, 37.2MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 43.0MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 43.1MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 39.7MB/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 4c97e256db..fb2ddd5cf3 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,13 +432,14 @@ 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]
- 13%|#3 | 5.84M/44.7M [00:00<00:00, 61.3MB/s]
- 26%|##6 | 11.7M/44.7M [00:00<00:00, 51.4MB/s]
- 47%|####7 | 21.2M/44.7M [00:00<00:00, 71.3MB/s]
- 63%|######3 | 28.2M/44.7M [00:00<00:00, 68.9MB/s]
- 78%|#######8 | 35.0M/44.7M [00:00<00:00, 66.4MB/s]
- 93%|#########2| 41.4M/44.7M [00:00<00:00, 62.5MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 62.9MB/s]
+ 14%|#4 | 6.30M/44.7M [00:00<00:00, 51.0MB/s]
+ 30%|##9 | 13.2M/44.7M [00:00<00:00, 61.9MB/s]
+ 43%|####3 | 19.2M/44.7M [00:00<00:00, 62.1MB/s]
+ 56%|#####6 | 25.2M/44.7M [00:00<00:00, 62.2MB/s]
+ 70%|######9 | 31.2M/44.7M [00:00<00:00, 52.7MB/s]
+ 83%|########3 | 37.2M/44.7M [00:00<00:00, 55.8MB/s]
+ 99%|#########8| 44.2M/44.7M [00:00<00:00, 55.7MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 57.1MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 49e00ab0ad..1798eab99f 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -649,7 +649,7 @@ 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 24.204 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 23.283 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 c8f2576a3f..4aef64412e 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:36.287</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:28.001</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:24.204</p></td>
+<td><p>01:23.283</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>01:21.209</p></td>
+<td><p>01:18.654</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:55.065</p></td>
+<td><p>00:52.164</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>00:36.913</p></td>
+<td><p>00:36.646</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>00:31.763</p></td>
+<td><p>00:30.991</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>00:30.834</p></td>
+<td><p>00:30.942</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>00:26.929</p></td>
+<td><p>00:27.500</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>00:25.263</p></td>
+<td><p>00:24.454</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>00:21.363</p></td>
+<td><p>00:20.704</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>00:02.742</p></td>
+<td><p>00:02.662</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 4a24f62d72..18e72a284b 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -920,7 +920,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2686.8386 2686.5596 2689.3464 2684.8712 1.3741
+ 2682.4603 2682.0656 2684.9652 2681.1275 1.1873
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index cf1f83f8b4..dac17b82cc 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2502 16.0669 17.0351 15.9991 0.3813
+ 15.7550 15.7885 16.0648 15.4662 0.1803
</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 2af57c20b1..e534bdd45d 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,31 +454,32 @@ 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]
- 1%|1 | 2.05M/170M [00:00<00:12, 13.9MB/s]
- 3%|2 | 4.55M/170M [00:00<00:11, 15.7MB/s]
- 5%|4 | 7.99M/170M [00:00<00:09, 17.8MB/s]
- 9%|9 | 16.1M/170M [00:00<00:04, 35.9MB/s]
- 14%|#4 | 24.0M/170M [00:00<00:03, 39.3MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:02, 49.7MB/s]
- 24%|##3 | 40.0M/170M [00:01<00:02, 54.9MB/s]
- 28%|##8 | 48.0M/170M [00:01<00:02, 50.5MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 56.0MB/s]
- 38%|###7 | 64.0M/170M [00:01<00:02, 53.7MB/s]
- 42%|####2 | 72.0M/170M [00:01<00:02, 51.3MB/s]
- 48%|####8 | 82.1M/170M [00:01<00:01, 62.5MB/s]
- 52%|#####2 | 88.6M/170M [00:01<00:01, 52.8MB/s]
- 56%|#####5 | 94.3M/170M [00:02<00:01, 46.8MB/s]
- 61%|######1 | 104M/170M [00:02<00:01, 50.8MB/s]
- 68%|######7 | 115M/170M [00:02<00:00, 64.0MB/s]
- 72%|#######1 | 122M/170M [00:02<00:00, 56.4MB/s]
- 75%|#######5 | 128M/170M [00:02<00:00, 51.4MB/s]
- 80%|######## | 136M/170M [00:02<00:00, 55.7MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 58.9MB/s]
- 89%|########9 | 152M/170M [00:03<00:00, 52.7MB/s]
- 93%|#########2| 157M/170M [00:03<00:00, 51.2MB/s]
- 96%|#########5| 162M/170M [00:03<00:00, 49.2MB/s]
- 98%|#########8| 167M/170M [00:03<00:00, 45.7MB/s]
-100%|##########| 170M/170M [00:03<00:00, 48.7MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:03, 52.4MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:03, 44.2MB/s]
+ 11%|# | 18.5M/170M [00:00<00:03, 42.2MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:03, 44.3MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:02, 48.8MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:02, 55.4MB/s]
+ 28%|##8 | 48.0M/170M [00:00<00:02, 59.4MB/s]
+ 33%|###2 | 56.0M/170M [00:01<00:02, 59.3MB/s]
+ 38%|###7 | 64.0M/170M [00:01<00:01, 56.9MB/s]
+ 43%|####2 | 72.7M/170M [00:01<00:01, 65.3MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 60.7MB/s]
+ 52%|#####1 | 88.0M/170M [00:01<00:01, 59.3MB/s]
+ 56%|#####5 | 94.3M/170M [00:01<00:01, 43.5MB/s]
+ 60%|###### | 102M/170M [00:02<00:01, 50.7MB/s]
+ 64%|######3 | 108M/170M [00:02<00:01, 50.5MB/s]
+ 67%|######6 | 113M/170M [00:02<00:01, 46.2MB/s]
+ 71%|#######1 | 121M/170M [00:02<00:00, 53.8MB/s]
+ 75%|#######5 | 128M/170M [00:02<00:00, 50.7MB/s]
+ 78%|#######8 | 133M/170M [00:02<00:00, 49.3MB/s]
+ 81%|########1 | 138M/170M [00:02<00:00, 38.5MB/s]
+ 85%|########4 | 144M/170M [00:03<00:00, 41.3MB/s]
+ 89%|########9 | 152M/170M [00:03<00:00, 48.5MB/s]
+ 93%|#########3| 158M/170M [00:03<00:00, 41.5MB/s]
+ 96%|#########5| 163M/170M [00:03<00:00, 42.3MB/s]
+ 98%|#########8| 167M/170M [00:03<00:00, 41.6MB/s]
+100%|##########| 170M/170M [00:03<00:00, 49.0MB/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=& [...]
@@ -576,7 +577,7 @@ 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 37.503 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 28.185 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 34906fcddb..09266a767b 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -495,8 +495,8 @@ 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, 79.3MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 107MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 52.1MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 69.2MB/s]
</pre></div>
</div>
</div>
@@ -587,7 +587,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.7380 90.6503 94.9799 90.0971 0.5665
+ 90.2238 90.1525 91.7630 89.9451 0.2524
</pre></div>
</div>
<div class="admonition note">
@@ -626,7 +626,7 @@ 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 16.721 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.629 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 c51da34199..58161055b8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -580,7 +580,7 @@ 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)
- 121.5896 121.4800 124.8701 120.7038 0.5781
+ 119.9972 119.9753 122.4845 119.1450 0.4230
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ 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 28.812 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 27.874 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 5bfde2f36c..29d36bcddd 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -521,7 +521,7 @@ 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 44.807 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 45.632 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 d40bc05b9d..2b03c7d5d9 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,23 +463,23 @@ 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%|5 | 7089/132723 [00:00<00:01, 70878.41KB/s]
- 12%|#1 | 15621/132723 [00:00<00:01, 79365.25KB/s]
- 18%|#7 | 23558/132723 [00:00<00:01, 66153.21KB/s]
- 24%|##4 | 32181/132723 [00:00<00:01, 73220.56KB/s]
- 30%|##9 | 39721/132723 [00:00<00:01, 62616.44KB/s]
- 37%|###6 | 48491/132723 [00:00<00:01, 69843.82KB/s]
- 43%|####3 | 57152/132723 [00:00<00:01, 74728.71KB/s]
- 49%|####8 | 64916/132723 [00:00<00:00, 72665.03KB/s]
- 55%|#####4 | 72858/132723 [00:01<00:00, 74605.99KB/s]
- 61%|######1 | 81541/132723 [00:01<00:00, 78163.13KB/s]
- 67%|######7 | 89486/132723 [00:01<00:00, 68414.73KB/s]
- 74%|#######3 | 98207/132723 [00:01<00:00, 73444.61KB/s]
- 80%|######## | 106832/132723 [00:01<00:00, 76983.08KB/s]
- 86%|########6 | 114752/132723 [00:01<00:00, 66577.33KB/s]
- 93%|#########3| 123463/132723 [00:01<00:00, 71866.69KB/s]
-100%|#########9| 132236/132723 [00:01<00:00, 76133.22KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 72585.43KB/s]
+ 5%|4 | 6452/132723 [00:00<00:01, 64511.45KB/s]
+ 11%|#1 | 15045/132723 [00:00<00:01, 77104.98KB/s]
+ 17%|#7 | 22756/132723 [00:00<00:01, 71610.02KB/s]
+ 24%|##3 | 31210/132723 [00:00<00:01, 76481.23KB/s]
+ 29%|##9 | 38907/132723 [00:00<00:01, 75618.99KB/s]
+ 36%|###5 | 47428/132723 [00:00<00:01, 78784.74KB/s]
+ 42%|####2 | 55952/132723 [00:00<00:00, 80852.21KB/s]
+ 49%|####8 | 64453/132723 [00:00<00:00, 82155.76KB/s]
+ 55%|#####4 | 72944/132723 [00:00<00:00, 83006.09KB/s]
+ 61%|######1 | 81496/132723 [00:01<00:00, 83774.11KB/s]
+ 68%|######7 | 89883/132723 [00:01<00:00, 60149.44KB/s]
+ 74%|#######4 | 98288/132723 [00:01<00:00, 60774.88KB/s]
+ 80%|######## | 106298/132723 [00:01<00:00, 65389.12KB/s]
+ 86%|########6 | 114680/132723 [00:01<00:00, 60998.00KB/s]
+ 92%|#########2| 122698/132723 [00:01<00:00, 65606.81KB/s]
+ 99%|#########8| 131313/132723 [00:01<00:00, 70855.36KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 71272.32KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -518,7 +518,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 49.837 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 44.598 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 b57c9436d0..a82bd22161 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:30.774</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>15:09.256</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:49.837</p></td>
+<td><p>03:44.598</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>03:37.503</p></td>
+<td><p>03:28.185</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>02:28.812</p></td>
+<td><p>02:27.874</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>01:44.807</p></td>
+<td><p>01:45.632</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>01:16.721</p></td>
+<td><p>01:13.629</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>00:56.037</p></td>
+<td><p>00:55.372</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:42.102</p></td>
+<td><p>00:40.422</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:27.633</p></td>
+<td><p>00:27.002</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:27.317</p></td>
+<td><p>00:26.535</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
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 53124b7a73..818d754b92 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -619,7 +619,7 @@ 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.zipdcc918c2-ce94-4500-85b6-fb8331ff65cd 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.zipb7f38c14-2af6-4ab5-8353-12dcb164a542 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 07e11c063f..f78a504a67 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:54.759</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:55.128</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:50.841</p></td>
+<td><p>00:51.153</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>00:02.804</p></td>
+<td><p>00:02.839</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>00:01.105</p></td>
+<td><p>00:01.128</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 08630dcd02..20fa3ef023 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -526,10 +526,10 @@ 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: 23087us [23087us] (49.26%; 49.26%)
-FoldScaleAxis: 23782us [9us] (50.74%; 50.74%)
- FoldConstant: 23773us [1742us] (50.72%; 99.96%)
- InferType: 22032us [22032us] (47.01%; 92.67%)
+InferType: 22868us [22868us] (48.95%; 48.95%)
+FoldScaleAxis: 23848us [9us] (51.05%; 51.05%)
+ FoldConstant: 23838us [1835us] (51.03%; 99.96%)
+ InferType: 22004us [22004us] (47.10%; 92.30%)
</pre></div>
</div>
</div>
@@ -551,10 +551,10 @@ 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: 22225us [22225us] (48.40%; 48.40%)
-FoldScaleAxis: 23691us [7us] (51.60%; 51.60%)
- FoldConstant: 23684us [1766us] (51.58%; 99.97%)
- InferType: 21918us [21918us] (47.73%; 92.54%)
+InferType: 22283us [22283us] (48.34%; 48.34%)
+FoldScaleAxis: 23817us [7us] (51.66%; 51.66%)
+ FoldConstant: 23810us [1805us] (51.65%; 99.97%)
+ InferType: 22005us [22005us] (47.73%; 92.42%)
</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 3811f3dbf8..f8f5a43c6a 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -575,7 +575,7 @@ 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: 54.173217 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 42.803230 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 3fd62d33d5..9d2c01e791 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -867,7 +867,7 @@ 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: 13.364560 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.352287 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 b3ae0a9806..32051b2f28 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -472,8 +472,8 @@ 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: 0.019758
-Baseline: 3.213628
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018497
+Baseline: 3.425754
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -532,7 +532,7 @@ 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: 0.313545
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.298768
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ 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: 0.345987
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.338181
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -644,7 +644,7 @@ 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: 0.117049
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.116157
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -721,7 +721,7 @@ 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: 0.109335
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110427
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ 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: 0.111237
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.113422
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -879,7 +879,7 @@ 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: 0.147535
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147519
</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 68532dde38..85dd9e658f 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.078</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.164</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.194</p></td>
+<td><p>00:32.420</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>00:01.683</p></td>
+<td><p>00:01.628</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>00:01.201</p></td>
+<td><p>00:01.116</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 0bd9e91e4c..ac9a6c6c45 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:53.878</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:52.818</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>06:03.017</p></td>
+<td><p>06:04.984</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>01:42.731</p></td>
+<td><p>01:40.201</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>01:08.967</p></td>
+<td><p>01:07.959</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>00:31.119</p></td>
+<td><p>00:31.997</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>00:14.256</p></td>
+<td><p>00:14.082</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>00:13.788</p></td>
+<td><p>00:13.596</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 b0b1ed9b4e..ed45146491 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
@@ -506,44 +506,328 @@ class Module:
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": True, "global_symbol": "main", "tir.noalias": True})
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 16)
- conv2d_nchw = T.allocate([2], "float32", "local")
- pad_temp_shared = T.allocate([648], "float32", "shared")
- kernel_shared = T.allocate([2304], "float32", "shared")
+ T.launch_thread(blockIdx_x, 32)
+ conv2d_nchw = T.allocate([7], "float32", "local")
+ pad_temp_shared = T.allocate([4032], "float32", "shared")
+ kernel_shared = T.allocate([3072], "float32", "shared")
threadIdx_x = T.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 784)
- conv2d_nchw_1 = T.Buffer((1,), data=conv2d_nchw, scope="local", align=4)
+ T.launch_thread(threadIdx_x, 112)
+ conv2d_nchw_1 = T.Buffer((7,), data=conv2d_nchw, scope="local", align=16)
conv2d_nchw_1[0] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- for rc_outer_outer in range(64):
- cse_var_1: T.int32 = rc_outer_outer * 72
+ conv2d_nchw_1[2] = T.float32(0)
+ conv2d_nchw_1[3] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
+ conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
+ for rc_outer_outer, ry_outer_outer in T.grid(8, 3):
+ cse_var_4: T.int32 = rc_outer_outer * 3136
+ cse_var_3: T.int32 = rc_outer_outer * 576
+ cse_var_2: T.int32 = ry_outer_outer * 7
+ cse_var_1: T.int32 = ry_outer_outer * 3
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((648,), data=pad_temp_shared, scope="shared")
- with T.launch_thread(threadIdx_x_1, 784):
- if T.likely(threadIdx_x_1 < 648):
- data_1 = T.Buffer((25088,), data=data.data)
- pad_temp_shared_1[threadIdx_x_1] = T.if_then_else(9 <= threadIdx_x_1 % 81 and threadIdx_x_1 % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[rc_outer_outer * 392 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
+ pad_temp_shared_1 = T.Buffer((4032,), data=pad_temp_shared, scope="shared")
+ data_1 = T.Buffer((25088,), data=data.data)
+ with T.launch_thread(threadIdx_x_1, 112):
+ pad_temp_shared_1[threadIdx_x_1 * 16] = T.if_then_else(1 <= threadIdx_x_1 * 16 % 63 // 9 + ry_outer_outer and threadIdx_x_1 * 16 % 63 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 7 % 9 and threadIdx_x_1 * 7 % 9 < 8, data_1[cse_var_4 + threadIdx_x_1 * 16 // 9 * 7 + cse_var_2 + threadIdx_x_1 * 7 % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 1) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 1) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 2] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 2) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 2) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 2) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 3) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 3) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 4] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 4) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 4) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 4) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 5] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 5) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 5) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 5) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 6] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 6) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 6) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 6) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 7] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 7) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 7) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 7) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 8] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 8) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 8) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 8) % 9 and (threadIdx_x_1 * 7 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 8) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 9] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 16 // 9 + 1) % 7 and ry_outer_outer + (threadIdx_x_1 * 16 // 9 + 1) % 7 < 8 and 1 <= threadIdx_x_1 * 7 % 9 and threadIdx_x_1 * 7 % 9 < 8, data_1[cse_var_4 + threadIdx_x_1 * 16 // 9 * 7 + cse_var_2 + threadIdx_x_1 * 7 % 9 - 1], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 10] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 10) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 10) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 10) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 11] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 11) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 11) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 11) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 12] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 12) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 12) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 12) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 13] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 13) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 13) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 13) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 14] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 14) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 14) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 14) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 15] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 15) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 15) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 15) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 112):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1792] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 28) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 28) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1792) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1793] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 29) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 29) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1793) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1794] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 30) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 30) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1794) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1795] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 31) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 31) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1795) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1796] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 32) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 32) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1796) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1797] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 33) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 33) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1797) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1798] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 34) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 34) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1798) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1799] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 35) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 35) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 8) % 9 and (threadIdx_x_1 * 7 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1799) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 8) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1800] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 16 // 9 + 4) % 7 and ry_outer_outer + (threadIdx_x_1 * 16 // 9 + 4) % 7 < 8 and 1 <= threadIdx_x_1 * 7 % 9 and threadIdx_x_1 * 7 % 9 < 8, data_1[cse_var_4 + threadIdx_x_1 * 16 // 9 * 7 + cse_var_2 + threadIdx_x_1 * 7 % 9 + 1392], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1801] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 37) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 37) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1801) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1802] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 38) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 38) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1802) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1803] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 39) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 39) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1803) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1804] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 40) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 40) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1804) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1805] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 41) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 41) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1805) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1806] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 42) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 42) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1806) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 1807] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 43) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 43) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 1807) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ with T.launch_thread(threadIdx_x_1, 112):
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3584] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 56) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 56) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3584) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3585] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 57) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 57) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3585) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3586] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 58) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 58) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3586) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3587] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 59) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 59) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3587) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3588] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 60) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 60) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3588) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3589] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 61) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 61) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3589) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3590] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 62) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 62) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 8) % 9 and (threadIdx_x_1 * 7 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3590) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 8) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3591] = T.if_then_else(1 <= threadIdx_x_1 * 16 % 63 // 9 + ry_outer_outer and threadIdx_x_1 * 16 % 63 // 9 + ry_outer_outer < 8 and 1 <= threadIdx_x_1 * 7 % 9 and threadIdx_x_1 * 7 % 9 < 8, data_1[cse_var_4 + threadIdx_x_1 * 16 // 9 * 7 + cse_var_2 + threadIdx_x_1 * 7 % 9 + 2785], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3592] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 1) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 1) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 1) % 9 and (threadIdx_x_1 * 7 + 1) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3592) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 1) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3593] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 2) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 2) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 2) % 9 and (threadIdx_x_1 * 7 + 2) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3593) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 2) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3594] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 3) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 3) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 3) % 9 and (threadIdx_x_1 * 7 + 3) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3594) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 3) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3595] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 4) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 4) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 4) % 9 and (threadIdx_x_1 * 7 + 4) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3595) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 4) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3596] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 5) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 5) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 5) % 9 and (threadIdx_x_1 * 7 + 5) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3596) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 5) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3597] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 6) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 6) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 6) % 9 and (threadIdx_x_1 * 7 + 6) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3597) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 6) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3598] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 7) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 7) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 7) % 9 and (threadIdx_x_1 * 7 + 7) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3598) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 7) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 28):
+ pad_temp_shared_1[threadIdx_x_1 * 16 + 3599] = T.if_then_else(1 <= (threadIdx_x_1 * 16 + 8) % 63 // 9 + ry_outer_outer and (threadIdx_x_1 * 16 + 8) % 63 // 9 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 7 + 8) % 9 and (threadIdx_x_1 * 7 + 8) % 9 < 8, data_1[cse_var_4 + (threadIdx_x_1 * 16 + 3599) // 9 * 7 + cse_var_2 + (threadIdx_x_1 * 7 + 8) % 9 - 8], T.float32(0))
threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((2304,), data=kernel_shared, scope="shared")
+ kernel_shared_1 = T.Buffer((3072,), data=kernel_shared, scope="shared")
kernel_1 = T.Buffer((2359296,), data=kernel.data)
- with T.launch_thread(threadIdx_x_2, 784):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 147456 + threadIdx_x_2 // 72 * 4608 + cse_var_1 + threadIdx_x_2 % 72]
- with T.launch_thread(threadIdx_x_2, 784):
- kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 784) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 72 // 3 * 3 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 784):
- if T.likely(threadIdx_x_2 < 736):
- kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 147456 + (threadIdx_x_2 + 1568) // 72 * 4608 + cse_var_1 + (threadIdx_x_2 + 56) % 72 // 3 * 3 + (threadIdx_x_2 + 2) % 3]
- for rc_outer_inner, ry_outer_inner in T.grid(8, 3):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 1152]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 1]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 1153]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 2]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 81 + threadIdx_x % 49 // 7 * 9 + ry_outer_inner * 9 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 49 * 72 + rc_outer_inner * 9 + ry_outer_inner * 3 + 1154]
- compute_1 = T.Buffer((25088,), data=compute.data)
- bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 1568 + threadIdx_x] = T.max(conv2d_nchw_1[0] + bias_1[blockIdx_x * 32 + threadIdx_x // 49], T.float32(0))
- compute_1[blockIdx_x * 1568 + threadIdx_x + 784] = T.max(conv2d_nchw_1[1] + bias_1[blockIdx_x * 32 + threadIdx_x // 49 + 16], T.float32(0))
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 73728 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 112] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 112) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 112) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 224] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 224) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 336) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 48) % 64 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 448] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 448) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 560] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 560) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 176) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 672) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 32) % 64 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 784) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 896] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 896) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 128) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1008] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1008) // 192 * 4608 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 144]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1120] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1120) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 160) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1232] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1232) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1344] = kernel_1[blockIdx_x * 73728 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 32256]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1456] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1456) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 112) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1568) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1680] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1680) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 48) % 64 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1792] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1792) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 1904] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 1904) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 176) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2016] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2016) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 32) % 64 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2128] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2128) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2240] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2240) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 128) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2352] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2352) // 192 * 4608 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 144]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2464] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2464) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 160) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2576] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2576) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2688] = kernel_1[blockIdx_x * 73728 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 64512]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2800] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2800) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 112) % 192 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ kernel_shared_1[threadIdx_x_2 + 2912] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 2912) // 192 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 112):
+ if T.likely(threadIdx_x_2 < 48):
+ kernel_shared_1[threadIdx_x_2 + 3024] = kernel_1[blockIdx_x * 73728 + (threadIdx_x_2 + 3024) // 192 * 4608 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 432]
+ for rc_outer_inner in range(8):
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 81] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 90] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 99] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 108] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 117] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 82] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 91] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 100] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 109] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 118] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 4]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 83] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 92] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 101] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 110] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 119] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 5]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 126] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 135] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 144] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 153] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 162] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 171] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 180] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 127] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 136] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 145] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 154] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 163] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 172] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 181] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 128] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 137] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 146] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 155] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 164] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 173] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 182] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 189] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 198] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 207] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 216] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 225] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 234] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 243] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 9]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 190] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 199] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 208] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 217] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 226] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 235] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 244] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 10]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 191] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 200] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 209] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 218] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 227] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 236] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 245] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 11]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 252] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 261] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 270] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 279] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 288] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 297] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 306] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 253] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 262] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 271] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 280] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 289] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 298] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 307] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 254] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 263] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 272] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 281] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 290] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 299] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 308] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 315] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 324] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 333] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 342] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 351] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 360] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 369] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 15]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 316] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 325] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 334] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 343] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 352] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 361] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 370] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 16]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 317] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 326] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 335] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 344] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 353] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 362] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 371] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 17]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 378] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 387] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 396] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 405] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 414] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 423] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 432] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 379] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 388] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 397] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 406] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 415] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 424] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 433] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 380] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 389] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 398] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 407] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 416] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 425] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 434] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 441] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 450] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 459] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 468] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 477] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 486] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 495] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 21]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 442] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 451] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 460] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 469] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 478] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 487] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 496] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 22]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 443] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 452] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 461] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 470] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 479] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 488] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 504 + threadIdx_x % 7 + 497] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 24 + 23]
+ for i2_inner in range(7):
+ compute_1 = T.Buffer((25088,), data=compute.data)
+ bias_1 = T.Buffer((512,), data=bias.data)
+ compute_1[blockIdx_x * 784 + threadIdx_x // 7 * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[i2_inner] + bias_1[blockIdx_x * 16 + threadIdx_x // 7], T.float32(0))
</pre></div>
</div>
</div>
@@ -577,7 +861,7 @@ 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: 0.325 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.335 ms
</pre></div>
</div>
</div>
@@ -609,19 +893,19 @@ 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=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
-conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=8)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=8)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=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=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 [...]
@@ -630,9 +914,9 @@ compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -655,14 +939,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=784)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=16)
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=784)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -680,36 +964,306 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(784) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[2];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[2304];
+extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- __syncthreads();
- if (((int)threadIdx.x) < 648) {
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 736) {
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1152)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1153)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 81) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((((int)threadIdx.x) / 49) * 72) + (rc_outer_inner * 9)) + (ry_outer_inner * 3)) + 1154)]));
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[(((int)threadIdx.x) * 16)] = (((((1 <= ((((((int)threadIdx.x) * 16) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) * 16) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 2) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 4) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 4) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 5) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 5) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 5) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 6)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 6) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 6) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 6) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 7)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 7) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 8)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 8) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 9)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 16) / 9) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 16) / 9) + 1) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) * 16) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 1)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 10)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 10) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 10) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 10) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 11)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 11) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 11) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 11) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 12)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 12) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 12) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 12) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 13)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 13) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 13) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 13) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 14)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 14) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 15)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 15) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1792)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1792) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1793)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1793) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1794)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1794) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1795)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1795) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1796)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 32) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 32) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1796) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1797)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 33) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 33) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1797) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1798)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 34) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 34) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1798) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1799)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1799) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1800)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 16) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 16) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) * 16) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 7) % 9)) + 1392)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1801)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 37) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 37) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1801) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1802)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 38) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 38) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1802) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1803)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 39) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 39) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1803) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1804)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 40) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 40) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1804) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1805)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 41) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 41) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1805) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1806)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1806) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - [...]
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 1807)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 1807) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - [...]
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3584)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3584) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3585)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3585) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3586)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 58) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 58) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3586) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3587)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 59) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 59) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3587) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3588)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 60) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 60) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3588) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3589)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 61) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 61) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3589) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3590)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 62) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 62) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3590) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3591)] = (((((1 <= ((((((int)threadIdx.x) * 16) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) * 16) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 7) % 9)) + 2785)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3592)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3592) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3593)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3593) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3594)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3594) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3595)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 4) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3595) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3596)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 5) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 5) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3596) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3597)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 6) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 6) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3597) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3598)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3598) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - [...]
+ }
+ if (((int)threadIdx.x) < 28) {
+ pad_temp_shared[((((int)threadIdx.x) * 16) + 3599)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 16) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + ((((((int)threadIdx.x) * 16) + 3599) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - [...]
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 48) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 160) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1680) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 48) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1792) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1904) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 176) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2016) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) / 3) + 32) & 63) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2128) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2240) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 128) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2464) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 160) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2576) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2800) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((((int)threadIdx.x) + 112) % 192) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2912) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 48) {
+ kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3024) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 432)];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 8; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 504) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 360)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 369)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 352)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 361)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 370)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 353)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 362)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 371)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 387)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 396)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 432)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 388)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 397)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 433)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 389)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 398)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 434)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 450)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 459)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 468)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 451)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 460)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 478)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 452)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 461)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 479)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 504) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 24)) + 23)]));
}
}
}
- compute[((((int)blockIdx.x) * 1568) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 1568) + ((int)threadIdx.x)) + 784)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) * 32) + (((int)threadIdx.x) / 49)) + 16)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
+ }
}
</pre></div>
</div>
@@ -743,7 +1297,7 @@ 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 3.017 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 4.984 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 bd18c521b6..1d2062540d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -916,7 +916,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.9416 7.9379 7.9533 7.9337 0.0084
+ 7.9007 7.8993 7.9091 7.8938 0.0063
</pre></div>
</div>
</div>
@@ -938,7 +938,7 @@ 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 8.967 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.959 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 520099ceb7..d916759ad0 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -935,7 +935,7 @@ 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)
- 754.5451 754.5061 758.2794 750.8499 3.0332
+ 751.7400 751.7110 753.7671 749.7419 1.6434
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ 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 42.731 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 40.201 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 0a3bda8b54..8f5991c440 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -632,74 +632,75 @@ 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": True, "global_symbol": "main", "tir.noalias": True})
- for i0_outer_i1_outer_fused in T.parallel(64):
- compute_1 = T.allocate([1024], "float32", "global")
- compute_2 = T.Buffer((1024,), data=compute_1)
- for 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(cse_var_2, i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 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)
- 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_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))
+ for i0_outer in T.parallel(2):
+ compute_1 = T.allocate([2048], "float32", "global")
+ for i1_outer in range(16):
+ compute_2 = T.Buffer((2048,), data=compute_1)
+ for nb_j_inner in range(2):
+ for i_inner_init in range(64):
+ 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(cse_var_2, i1_outer * 2 + nb_j_inner, placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2]), 64):
+ 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 = i1_outer * 2 + nb_j_inner
+ cse_var_19: T.int32 = i0_outer * 16384 + i_inner * 256
+ cse_var_18: T.int32 = i_inner * 32 + nb_j_inner * 16
+ cse_var_17: T.int32 = cse_var_18 + 9
+ cse_var_16: T.int32 = cse_var_18 + 8
+ cse_var_15: T.int32 = cse_var_18 + 7
+ cse_var_14: T.int32 = cse_var_18 + 6
+ cse_var_13: T.int32 = cse_var_18 + 5
+ cse_var_12: T.int32 = cse_var_18 + 4
+ cse_var_11: T.int32 = cse_var_18 + 3
+ cse_var_10: T.int32 = cse_var_18 + 2
+ cse_var_9: T.int32 = cse_var_18 + 15
+ cse_var_8: T.int32 = cse_var_18 + 14
+ cse_var_7: T.int32 = cse_var_18 + 13
+ cse_var_6: T.int32 = cse_var_18 + 12
+ cse_var_5: T.int32 = cse_var_18 + 11
+ cse_var_4: T.int32 = cse_var_18 + 10
+ cse_var_3: T.int32 = cse_var_18 + 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)
+ compute_2[cse_var_18] = compute_2[cse_var_18] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_3] = compute_2[cse_var_3] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 1] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_10] = compute_2[cse_var_10] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 2] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_11] = compute_2[cse_var_11] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 3] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_12] = compute_2[cse_var_12] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 4] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_13] = compute_2[cse_var_13] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 5] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_14] = compute_2[cse_var_14] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 6] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_15] = compute_2[cse_var_15] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 7] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_16] = compute_2[cse_var_16] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 8] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_17] = compute_2[cse_var_17] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 9] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_4] = compute_2[cse_var_4] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 10] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_5] = compute_2[cse_var_5] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 11] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_6] = compute_2[cse_var_6] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 12] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_7] = compute_2[cse_var_7] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 13] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_8] = compute_2[cse_var_8] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 14] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ compute_2[cse_var_9] = compute_2[cse_var_9] + placeholder_6[placeholder_5[cse_var_20] * 16 + cse_var_21 + 15] * T.max(placeholder_7[cse_var_19 + placeholder_8[placeholder_5[cse_var_20] + elem_idx]], T.float32(0))
+ for i0_inner in range(64):
+ cse_var_22: T.int32 = i0_outer * 32768 + i0_inner * 512 + i1_outer * 32
+ compute_3 = T.Buffer((65536,), data=compute.data)
+ placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
+ 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>
@@ -733,7 +734,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.774 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.843 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 208d925922..99f9842d36 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:47.214</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:39.018</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:47.181</p></td>
+<td><p>00:38.983</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.022</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 6239b118d0..d4d69256dd 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -690,7 +690,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10200261
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8562924
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -813,7 +813,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1076591
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5015952
No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -936,8 +936,11 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1269484
-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, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 32, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5473682
+No: 4 GFLOPS: 3.78/3.78 result: MeasureResult(costs=(0.06130134575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3446884155273438, timestamp=1677093024.1845086) [('tile_f', [-1, 8, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5653298
+No: 5 GFLOPS: 54.52/54.52 result: MeasureResult(costs=(0.004246405,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.205479145050049, timestamp=1677093033.119018) [('tile_f', [-1, 4, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6203369
+No: 6 GFLOPS: 1.17/54.52 result: MeasureResult(costs=(0.19841366575,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.517274379730225, timestamp=1677093036.1125317) [('tile_f', [-1, 2, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7067931
+No: 7 GFLOPS: 0.00/54.52 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1059,8 +1062,9 @@ 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, 4, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4194246
-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, 1, 8, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6356639
+No: 8 GFLOPS: 6.94/54.52 result: MeasureResult(costs=(0.0333526725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5584919452667236, timestamp=1677093036.9794106) [('tile_f', [-1, 2, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5599505
+No: 9 GFLOPS: 0.00/54.52 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1182,26 +1186,8 @@ 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, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7373012
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
- res = future.result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
- return self.__get_result()
- File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
- raise self._exception
- File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
- result = self.fn(*self.args, **self.kwargs)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
- worker = lambda *args: self._worker_run(*args)
- File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
- return proc.recv()
- File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
- raise TimeoutError()
-TimeoutError
-
- [('tile_f', [-1, 64, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8338281
-No: 7 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, 1, 128, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6099109
+No: 10 GFLOPS: 0.00/54.52 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
@@ -1323,9 +1309,8 @@ 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, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3863343
-No: 8 GFLOPS: 4.26/4.26 result: MeasureResult(costs=(0.05434336075,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.968520164489746, timestamp=1677092167.710194) [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1008886
-No: 9 GFLOPS: 0.00/4.26 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, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6944217
+No: 11 GFLOPS: 0.00/54.52 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
@@ -1447,11 +1432,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8321796
-No: 10 GFLOPS: 212.32/212.32 result: MeasureResult(costs=(0.0010903599673913044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4794631004333496, timestamp=1677092171.4352517) [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7944290
-No: 11 GFLOPS: 58.66/212.32 result: MeasureResult(costs=(0.00394652673076923,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.2472450733184814, timestamp=1677092172.198755) [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7090860
-No: 12 GFLOPS: 24.20/212.32 result: MeasureResult(costs=(0.009564948272727273,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8552525043487549, timestamp=1677092172.9754047) [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5824490
-No: 13 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 64, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3574785
+No: 12 GFLOPS: 0.00/54.52 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
@@ -1573,8 +1555,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,929090
-No: 14 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,602564
+No: 13 GFLOPS: 290.42/290.42 result: MeasureResult(costs=(0.0007971163834586467,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2988348007202148, timestamp=1677093038.6338923) [('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4187068
+No: 14 GFLOPS: 0.00/290.42 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
@@ -1696,8 +1679,8 @@ 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, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4081975
-No: 15 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8694834
+No: 15 GFLOPS: 0.00/290.42 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
@@ -1819,8 +1802,8 @@ 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, 4, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5031475
-No: 16 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 32, 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, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7307562
+No: 16 GFLOPS: 0.00/290.42 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
@@ -1942,8 +1925,8 @@ 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, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,922227
-No: 17 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3199976
+No: 17 GFLOPS: 0.00/290.42 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
@@ -2065,9 +2048,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1327363
-No: 18 GFLOPS: 4.87/212.32 result: MeasureResult(costs=(0.047576824000000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.651504755020142, timestamp=1677092178.0493603) [('tile_f', [-1, 1, 4, 16]), ('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, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3750515
-No: 19 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5860480
+No: 18 GFLOPS: 0.00/290.42 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
@@ -2189,160 +2171,131 @@ 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, 4, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3044787
-No: 20 GFLOPS: 0.00/212.32 result: Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 742, in __call__
- yield remote, remote.load_module(os.path.split(build_result.filename)[1])
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/workspace/python/tvm/runtime/module.py", line 357, in evaluator
- blob = feval(*args)
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 256]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9890097
+No: 19 GFLOPS: 38.97/290.42 result: MeasureResult(costs=(0.005941232736842105,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.738960027694702, timestamp=1677093041.6009665) [('tile_f', [-1, 2, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('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', 512), ('unroll_explicit', 0)],None,2081940
+No: 20 GFLOPS: 0.00/290.42 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 262, in tvm._ffi._cy3.core.FuncCall
- File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
- 4: TVMFuncCall
+ 24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
- 3: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
- 2: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
- at ../src/runtime/rpc/rpc_module.cc:129
- 1: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1012
- 0: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
- at ../src/runtime/rpc/rpc_endpoint.cc:804
- File "../src/runtime/rpc/rpc_endpoint.cc", line 804
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=kShutdown
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 706, in run_through_rpc
- costs = time_f(*args).results
- File "/usr/lib/python3.7/contextlib.py", line 130, in __exit__
- self.gen.throw(type, value, traceback)
- File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 746, in __call__
- remote.remove(build_result.filename)
- File "/workspace/python/tvm/rpc/client.py", line 144, in remove
- self._remote_funcs["remove"] = self.get_function("tvm.rpc.server.remove")
- File "/workspace/python/tvm/rpc/client.py", line 72, in get_function
- return self._sess.get_function(name)
- File "/workspace/python/tvm/runtime/module.py", line 171, in get_function
- self.handle, c_str(name), ctypes.c_int(query_imports), ctypes.byref(ret_handle)
- File "/workspace/python/tvm/_ffi/base.py", line 348, in check_call
- raise get_last_ffi_error()
-tvm._ffi.base.TVMError: Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCallKeywords
- 18: _PyEval_EvalFrameDefault
- 17: _PyFunction_FastCallKeywords
- 16: _PyEval_EvalCodeWithName
- 15: _PyEval_EvalFrameDefault
- 14: 0x0000000000537c30
- 13: _PyObject_FastCallKeywords
- 12: 0x00007efdb9eaffa2
- 11: _ctypes_callproc
- 10: ffi_call
- 9: ffi_call_unix64
- 8: TVMModGetFunction
- at ../src/runtime/c_runtime_api.cc:408
- 7: tvm::runtime::ModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool)
- at ../src/runtime/module.cc:66
- 6: tvm::runtime::RPCModuleNode::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)
- at ../src/runtime/rpc/rpc_module.cc:185
- 5: tvm::runtime::RPCClientSession::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.cc:1007
- 4: tvm::runtime::TVMRetValue tvm::runtime::RPCEndpoint::SysCallRemote<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(tvm::runtime::RPCCode, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)
- at ../src/runtime/rpc/rpc_endpoint.h:223
- 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&>(int&&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) const
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1621
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
- at ../src/runtime/rpc/rpc_endpoint.cc:684
- File "../src/runtime/rpc/rpc_endpoint.cc", line 684
-TVMError:
----------------------------------------------------------------
-An error occurred during the execution of TVM.
-For more information, please see: https://tvm.apache.org/docs/errors.html
----------------------------------------------------------------
- Check failed: (code == RPCCode::kReturn) is false: code=1
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
- 52: 0xffffffffffffffff
- 51: _start
- 50: __libc_start_main
- 49: _Py_UnixMain
- 48: 0x0000000000650da0
- 47: 0x0000000000650afa
- 46: _PyFunction_FastCallDict
- 45: _PyEval_EvalCodeWithName
- 44: _PyEval_EvalFrameDefault
- 43: _PyFunction_FastCallKeywords
- 42: _PyEval_EvalCodeWithName
- 41: _PyEval_EvalFrameDefault
- 40: _PyMethodDef_RawFastCallKeywords
- 39: 0x0000000000546369
- 38: _PyEval_EvalCodeWithName
- 37: _PyEval_EvalFrameDefault
- 36: _PyFunction_FastCallKeywords
- 35: _PyEval_EvalCodeWithName
- 34: _PyEval_EvalFrameDefault
- 33: _PyFunction_FastCallDict
- 32: _PyEval_EvalCodeWithName
- 31: _PyEval_EvalFrameDefault
- 30: _PyObject_FastCallDict
- 29: 0x00000000004c06e1
- 28: _PyFunction_FastCallDict
- 27: _PyEval_EvalFrameDefault
- 26: _PyMethodDescr_FastCallKeywords
- 25: 0x00000000005dcb58
- 24: 0x00000000005dc83f
- 23: 0x00000000004ba127
- 22: _PyEval_EvalFrameDefault
- 21: _PyFunction_FastCallKeywords
- 20: _PyEval_EvalFrameDefault
- 19: _PyFunction_FastCall [('tile_f', [-1, 2, 2, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2032785
+ 24: TVMFuncCall
+ at ../src/runtime/c_runtime_api.cc:477
+ 23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 22: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 21: operator()
+ at ../include/tvm/runtime/packed_func.h:1734
+ 20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
+ at ../include/tvm/runtime/packed_func.h:1674
+ 19: run<>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 18: run<tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1634
+ 14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
+ at ../include/tvm/runtime/packed_func.h:1649
+ 13: operator()
+ at ../src/driver/driver_api.cc:402
+ 12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, tvm::GlobalVarSupply, bool)
+ at ../src/driver/driver_api.cc:388
+ 11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
+ at ../src/driver/driver_api.cc:283
+ 10: tvm::transform::Pass::operator()(tvm::IRModule) const
+ at ../src/ir/transform.cc:258
+ 9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:451
+ 7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/ir/transform.cc:274
+ 6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
+ at ../src/tir/ir/transform.cc:100
+ 5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
+ at ../include/tvm/runtime/packed_func.h:1753
+ 4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
+ at ../include/tvm/runtime/packed_func.h:1697
+ 3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
+ at ../include/tvm/runtime/packed_func.h:1621
+ 2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
+ at ../include/tvm/runtime/packed_func.h:1217
+ 1: Call
+ at ../include/tvm/runtime/packed_func.h:1213
+ 0: operator()
+ at ../src/runtime/c_runtime_api.cc:534
+ File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
+ raise InstantiationError("Skipped because of invalid gpu kernel")
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 128]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3124430
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2381,9 +2334,9 @@ and measure running time.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Finish loading 20 records
Best config:
-[('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7944290
+[('tile_f', [-1, 2, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4187068
Finish loading 20 records
-Time cost of this operator: 0.000779
+Time cost of this operator: 0.001220
</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 ad5b7d5d87..cde90a6bba 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -643,10 +643,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.5 98.714 (1, 2, 10, 10, 3) 2 1 [310.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.09 0.982 (1, 6, 10, 10) 1 1 [3.09]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.955 0.304 (1, 1, 10, 10, 3) 1 1 [0.955]
-Total_time - 314.545 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.7 98.39 (1, 2, 10, 10, 3) 2 1 [310.7]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 4.124 1.306 (1, 6, 10, 10) 1 1 [4.124]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.304 (1, 1, 10, 10, 3) 1 1 [0.96]
+Total_time - 315.785 - - - - -
</pre></div>
</div>
</div>
@@ -698,13 +698,13 @@ 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 136.4 98.116 (1, 6, 10, 10, 1) 2 1 [136.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.782 1.282 (1, 6, 10, 10) 1 1 [1.782]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.838 0.603 (1, 3, 10, 10, 1) 1 1 [0.838]
-Total_time - 139.019 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.9 97.418 (1, 6, 10, 10, 1) 2 1 [102.9]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.765 1.671 (1, 6, 10, 10) 1 1 [1.765]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.911 (1, 1, 10, 10, 3) 1 1 [0.962]
+Total_time - 105.627 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.324 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.343 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 362651b1bf..bbd3493d9f 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -454,7 +454,7 @@ 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]
-100%|##########| 3.42M/3.42M [00:00<00:00, 50.1MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 112MB/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.
@@ -580,7 +580,7 @@ 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 15.558 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.650 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 9b1b62e935..5c719628ed 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -523,7 +523,7 @@ 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/tmp3h4cg_60/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpo2jxte13/images/random'
</pre></div>
</div>
</div>
@@ -583,8 +583,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp3h4cg_60/images/target contains 8144 images
-/tmp/tmp3h4cg_60/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], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpo2jxte13/images/target contains 8144 images
+/tmp/tmpo2jxte13/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -696,13 +696,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2131 - accuracy: 0.9248 - val_loss: 0.1032 - val_accuracy: 0.9660 - 47s/epoch - 144ms/step
+328/328 - 47s - loss: 0.1876 - accuracy: 0.9340 - val_loss: 0.1708 - val_accuracy: 0.9407 - 47s/epoch - 145ms/step
Epoch 2/3
-328/328 - 43s - loss: 0.1025 - accuracy: 0.9623 - val_loss: 0.0837 - val_accuracy: 0.9694 - 43s/epoch - 132ms/step
+328/328 - 44s - loss: 0.0904 - accuracy: 0.9660 - val_loss: 0.1150 - val_accuracy: 0.9611 - 44s/epoch - 133ms/step
Epoch 3/3
-328/328 - 43s - loss: 0.0709 - accuracy: 0.9716 - val_loss: 0.0882 - val_accuracy: 0.9668 - 43s/epoch - 132ms/step
+328/328 - 43s - loss: 0.0647 - accuracy: 0.9766 - val_loss: 0.1037 - val_accuracy: 0.9611 - 43s/epoch - 132ms/step
-<keras.callbacks.History object at 0x7f7aef740f10>
+<keras.callbacks.History object at 0x7f1a8653c4d0>
</pre></div>
</div>
</div>
@@ -966,7 +966,7 @@ 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 55.274 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 51.267 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 113a750554..a20280d705 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:43.085</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:38.927</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">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>04:55.274</p></td>
+<td><p>04:51.267</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:15.558</p></td>
+<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>01:16.343</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:15.324</p></td>
+<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>01:14.650</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>00:09.840</p></td>
+<td><p>00:09.745</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:07.089</p></td>
+<td><p>00:06.923</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>
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 8699fb4543..a045e56d4b 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.834</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:45.622</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:33.995</p></td>
+<td><p>00:33.558</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.374</p></td>
+<td><p>00:10.277</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>00:01.459</p></td>
+<td><p>00:01.781</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 06c582ac8b..a9aae383fd 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f7995d549e0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f191f090680>
</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 50727893ba..4acda8a485 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.962</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:07.422</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,35 +349,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:02.370</p></td>
+<td><p>00:04.909</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>00:01.197</p></td>
+<td><p>00:01.149</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>00:00.592</p></td>
+<td><p>00:00.576</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>00:00.571</p></td>
+<td><p>00:00.560</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>00:00.118</p></td>
+<td><p>00:00.116</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.053</p></td>
+<td><p>00:00.052</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.033</p></td>
+<td><p>00:00.032</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.028</p></td>
+<td><p>00:00.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/install/nnpack.html b/docs/install/nnpack.html
index 1ef28de467..23d2181e9d 100644
--- a/docs/install/nnpack.html
+++ b/docs/install/nnpack.html
@@ -229,7 +229,17 @@
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Installing TVM</a><ul class="current">
-<li class="toctree-l2"><a class="reference internal" href="from_source.html">Install from Source</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="from_source.html">Install from Source</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#developers-get-source-from-github">Developers: Get Source from Github</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#build-the-shared-library">Build the Shared Library</a></li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#python-package-installation">Python Package Installation</a></li>
+<li class="toctree-l3 current"><a class="reference internal" href="from_source.html#install-contrib-libraries">Install Contrib Libraries</a><ul class="current">
+<li class="toctree-l4 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a></li>
+</ul>
+</li>
+<li class="toctree-l3"><a class="reference internal" href="from_source.html#enable-c-tests">Enable C++ Tests</a></li>
+</ul>
+</li>
<li class="toctree-l2"><a class="reference internal" href="docker.html">Docker Images</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">NNPACK Contrib Installation</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#conditions">Conditions</a></li>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index b5737709bf..1425b13d5a 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1616,7 +1616,7 @@ 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>
@@ -1900,7 +1900,7 @@ 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 bb2b3c80b6..748de91730 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/330fe8d17/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 73724f63c0..b556bfa526 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/330fe8d17/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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 12a7bf9074..9234352fff 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/330fe8d17/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index e46b0f4624..23502d81ab 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/330fe8d17/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index d4e3917520..2e1a0d2ed4 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/330fe8d17/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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 61c3b3193f..b71e920117 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/330fe8d17/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 97b618f441..82151426a2 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 1774232241..4c0ffe881e 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 3423ac12be..94611953df 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/330fe8d17/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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 4327685654..4af132b476 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 688d676525..001e148112 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/330fe8d17/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 8c818366bd..cdd2b393d1 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index f27cb345bc..14b9c06e34 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/330fe8d17/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index f54b67546b..a9943530ea 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/330fe8d17/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 0339f680ce..87cd4bd609 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/330fe8d17/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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 d74d484b5c..6c65d5cb38 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/330fe8d17/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 136c38d42e..b5ba562c22 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/330fe8d17/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index e74783e1ee..a335afc89e 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/330fe8d17/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 9b19d68041..b4ee75c3aa 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/330fe8d17/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 051fbb4cf3..782e59b34a 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/330fe8d17/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 6e77ef7e10..8b62b0b0f8 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 6d1394290f..653df6dd60 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/330fe8d17/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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 efd96cc21f..f93caca62b 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/330fe8d17/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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 359aee835e..7b699c5dcd 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/330fe8d17/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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/330fe8d17/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5f610f45a/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 4025dba736..e73e4022d3 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 d10c7da049..2b2454e0fa 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:31.411</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:31.471</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:31.404</p></td>
+<td><p>00:31.464</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 0dcfab9316..910ad3724c 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -583,7 +583,7 @@ 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 33.84s!
+resnet18_v1 inference graph built in 34.13s!
</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 6bb7b2af4a..94115c07f9 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -601,7 +601,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 22.92s!
+yolov3-tiny inference graph built in 23.03s!
</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 3a7d03bdc3..213202be66 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:40.644</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:41.295</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_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>00:50.665</p></td>
+<td><p>00:51.186</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>00:49.979</p></td>
+<td><p>00:50.108</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 1f591be9fc..301d26dd1e 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.174</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.215</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.694</p></td>
+<td><p>00:02.739</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>00:00.480</p></td>
+<td><p>00:00.476</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 88601acf74..c2764253a9 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.798</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.789</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.413</p></td>
+<td><p>00:00.410</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>00:00.385</p></td>
+<td><p>00:00.379</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 308ce23738..43b9004f78 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -569,7 +569,7 @@ 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: 95.598 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 97.372 ms
</pre></div>
</div>
</div>
@@ -631,6 +631,7 @@ resume the status and do more 5 trials.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
+*E
</pre></div>
</div>
</div>
@@ -641,7 +642,7 @@ 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 19.728 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 31.356 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 f66aa31ff3..da4e5a2983 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -680,16 +680,16 @@ 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: 2.37/2.37 result: MeasureResult(costs=(0.1133659352,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0658187866210938, timestamp=1677090586.4301212) [('tile_y', [-1, 8]), ('tile_x', [-1, 2])],None,13
-No: 2 GFLOPS: 1.95/2.37 result: MeasureResult(costs=(0.137694009,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.444455862045288, timestamp=1677090588.8943553) [('tile_y', [-1, 8]), ('tile_x', [-1, 1])],None,3
-No: 3 GFLOPS: 2.92/2.92 result: MeasureResult(costs=(0.09204769900000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7327921390533447, timestamp=1677090591.692557) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
-No: 4 GFLOPS: 10.99/10.99 result: MeasureResult(costs=(0.024420770799999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6710712909698486, timestamp=1677090593.4052145) [('tile_y', [-1, 512]), ('tile_x', [-1, 64])],None,69
-No: 5 GFLOPS: 11.71/11.71 result: MeasureResult(costs=(0.0229258542,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6419792175292969, timestamp=1677090594.2327821) [('tile_y', [-1, 32]), ('tile_x', [-1, 32])],None,55
-No: 6 GFLOPS: 8.53/11.71 result: MeasureResult(costs=(0.031466835400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7346043586730957, timestamp=1677090594.98831) [('tile_y', [-1, 512]), ('tile_x', [-1, 32])],None,59
-No: 7 GFLOPS: 11.00/11.71 result: MeasureResult(costs=(0.0244026304,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7283415794372559, timestamp=1677090596.693982) [('tile_y', [-1, 1]), ('tile_x', [-1, 64])],None,60
-No: 8 GFLOPS: 1.89/11.71 result: MeasureResult(costs=(0.1423389596,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5096585750579834, timestamp=1677090599.2308238) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 9 GFLOPS: 9.71/11.71 result: MeasureResult(costs=(0.0276583776,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.88291335105896, timestamp=1677090600.2276921) [('tile_y', [-1, 2]), ('tile_x', [-1, 128])],None,71
-No: 10 GFLOPS: 9.22/11.71 result: MeasureResult(costs=(0.029103458199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.674823522567749, timestamp=1677090600.9527621) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 1 GFLOPS: 13.31/13.31 result: MeasureResult(costs=(0.0201727872,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6522362232208252, timestamp=1677091472.3224754) [('tile_y', [-1, 128]), ('tile_x', [-1, 128])],None,77
+No: 2 GFLOPS: 9.04/13.31 result: MeasureResult(costs=(0.029683789999999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7252194881439209, timestamp=1677091473.0650053) [('tile_y', [-1, 512]), ('tile_x', [-1, 256])],None,89
+No: 3 GFLOPS: 9.33/13.31 result: MeasureResult(costs=(0.028760432600000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7017536163330078, timestamp=1677091474.8107634) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 4 GFLOPS: 11.24/13.31 result: MeasureResult(costs=(0.0238799922,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6349952220916748, timestamp=1677091475.455273) [('tile_y', [-1, 256]), ('tile_x', [-1, 256])],None,88
+No: 5 GFLOPS: 3.91/13.31 result: MeasureResult(costs=(0.0686975356,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3443591594696045, timestamp=1677091476.9354005) [('tile_y', [-1, 16]), ('tile_x', [-1, 8])],None,34
+No: 6 GFLOPS: 9.40/13.31 result: MeasureResult(costs=(0.028570181,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6913285255432129, timestamp=1677091478.6950269) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+No: 7 GFLOPS: 3.94/13.31 result: MeasureResult(costs=(0.0681957996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3592090606689453, timestamp=1677091481.1015615) [('tile_y', [-1, 32]), ('tile_x', [-1, 16])],None,45
+No: 8 GFLOPS: 2.34/13.31 result: MeasureResult(costs=(0.1144797644,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0604121685028076, timestamp=1677091483.1871216) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 9 GFLOPS: 9.95/13.31 result: MeasureResult(costs=(0.0269727044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7323205471038818, timestamp=1677091484.0323374) [('tile_y', [-1, 1]), ('tile_x', [-1, 128])],None,70
+No: 10 GFLOPS: 14.38/14.38 result: MeasureResult(costs=(0.018663065200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5849051475524902, timestamp=1677091484.5908012) [('tile_y', [-1, 32]), ('tile_x', [-1, 64])],None,65
</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 2e0e21e1fc..3774c1e2fa 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -558,7 +558,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 515.2758335699855, 'median': 515.3482555999744, 'std': 1.2878188221012696}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 512.0541001199969, 'median': 511.61899980000385, 'std': 1.4801657422214596}
</pre></div>
</div>
</div>
@@ -710,179 +710,177 @@ 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: 12.35/ 14.99 GFLOPS | Progress: (4/20) | 11.41 s
-[Task 1/25] Current/Best: 6.44/ 14.99 GFLOPS | Progress: (8/20) | 16.48 s
-[Task 1/25] Current/Best: 12.58/ 21.68 GFLOPS | Progress: (12/20) | 19.79 s
-[Task 1/25] Current/Best: 12.35/ 22.53 GFLOPS | Progress: (16/20) | 25.69 s
-[Task 1/25] Current/Best: 4.26/ 22.53 GFLOPS | Progress: (20/20) | 30.23 s Done.
+[Task 1/25] Current/Best: 23.09/ 23.09 GFLOPS | Progress: (4/20) | 9.78 s
+[Task 1/25] Current/Best: 11.76/ 23.09 GFLOPS | Progress: (8/20) | 13.48 s
+[Task 1/25] Current/Best: 12.90/ 23.33 GFLOPS | Progress: (12/20) | 16.69 s
+[Task 1/25] Current/Best: 10.99/ 23.33 GFLOPS | Progress: (16/20) | 20.76 s
+[Task 1/25] Current/Best: 8.60/ 23.33 GFLOPS | Progress: (20/20) | 24.04 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 14.80/ 16.06 GFLOPS | Progress: (4/20) | 4.56 s
-[Task 2/25] Current/Best: 13.13/ 17.17 GFLOPS | Progress: (8/20) | 6.59 s
-[Task 2/25] Current/Best: 3.62/ 21.60 GFLOPS | Progress: (12/20) | 8.25 s
-[Task 2/25] Current/Best: 17.34/ 21.60 GFLOPS | Progress: (16/20) | 9.96 s
-[Task 2/25] Current/Best: 11.65/ 21.60 GFLOPS | Progress: (20/20) | 11.68 s Done.
+[Task 2/25] Current/Best: 20.43/ 20.43 GFLOPS | Progress: (4/20) | 4.11 s
+[Task 2/25] Current/Best: 12.96/ 20.43 GFLOPS | Progress: (8/20) | 6.44 s
+[Task 2/25] Current/Best: 11.60/ 20.43 GFLOPS | Progress: (12/20) | 7.94 s
+[Task 2/25] Current/Best: 9.98/ 20.43 GFLOPS | Progress: (16/20) | 9.88 s
+[Task 2/25] Current/Best: 6.11/ 20.43 GFLOPS | Progress: (20/20) | 11.63 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 19.37/ 19.37 GFLOPS | Progress: (4/20) | 4.57 s
-[Task 3/25] Current/Best: 6.99/ 19.37 GFLOPS | Progress: (8/20) | 6.97 s
-[Task 3/25] Current/Best: 17.51/ 19.37 GFLOPS | Progress: (12/20) | 10.01 s
-[Task 3/25] Current/Best: 16.70/ 23.22 GFLOPS | Progress: (16/20) | 12.88 s
-[Task 3/25] Current/Best: 10.17/ 23.22 GFLOPS | Progress: (20/20) | 15.43 s Done.
+[Task 3/25] Current/Best: 12.40/ 17.10 GFLOPS | Progress: (4/20) | 4.81 s
+[Task 3/25] Current/Best: 22.55/ 22.55 GFLOPS | Progress: (8/20) | 6.75 s
+[Task 3/25] Current/Best: 17.63/ 22.55 GFLOPS | Progress: (12/20) | 9.04 s
+[Task 3/25] Current/Best: 6.98/ 22.55 GFLOPS | Progress: (16/20) | 12.75 s
+[Task 3/25] Current/Best: 12.54/ 22.55 GFLOPS | Progress: (20/20) | 15.56 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 13.92/ 17.58 GFLOPS | Progress: (4/20) | 4.64 s
-[Task 4/25] Current/Best: 22.05/ 22.05 GFLOPS | Progress: (8/20) | 6.62 s
-[Task 4/25] Current/Best: 15.74/ 22.05 GFLOPS | Progress: (12/20) | 13.60 s
-[Task 4/25] Current/Best: 14.40/ 22.05 GFLOPS | Progress: (16/20) | 15.85 s
-[Task 4/25] Current/Best: 5.28/ 22.05 GFLOPS | Progress: (20/20) | 20.12 s Done.
+[Task 4/25] Current/Best: 20.98/ 20.98 GFLOPS | Progress: (4/20) | 4.67 s
+[Task 4/25] Current/Best: 5.08/ 21.83 GFLOPS | Progress: (8/20) | 9.88 s
+[Task 4/25] Current/Best: 7.02/ 21.83 GFLOPS | Progress: (12/20) | 11.83 s
+[Task 4/25] Current/Best: 6.21/ 21.83 GFLOPS | Progress: (16/20) | 14.27 s
+[Task 4/25] Current/Best: 2.08/ 21.83 GFLOPS | Progress: (20/20) | 17.41 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 19.77/ 19.77 GFLOPS | Progress: (4/20) | 4.32 s
-[Task 5/25] Current/Best: 3.26/ 19.77 GFLOPS | Progress: (8/20) | 6.78 s
-[Task 5/25] Current/Best: 5.97/ 19.77 GFLOPS | Progress: (12/20) | 8.87 s
-[Task 5/25] Current/Best: 19.30/ 19.77 GFLOPS | Progress: (16/20) | 10.70 s
-[Task 5/25] Current/Best: 3.99/ 19.77 GFLOPS | Progress: (20/20) | 13.13 s Done.
+[Task 5/25] Current/Best: 10.59/ 15.97 GFLOPS | Progress: (4/20) | 4.73 s
+[Task 5/25] Current/Best: 15.28/ 15.97 GFLOPS | Progress: (8/20) | 7.03 s
+[Task 5/25] Current/Best: 13.04/ 19.04 GFLOPS | Progress: (12/20) | 8.81 s
+[Task 5/25] Current/Best: 12.84/ 19.04 GFLOPS | Progress: (16/20) | 11.38 s
+[Task 5/25] Current/Best: 12.90/ 22.77 GFLOPS | Progress: (20/20) | 13.57 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 16.33/ 16.33 GFLOPS | Progress: (4/20) | 4.80 s
-[Task 6/25] Current/Best: 22.40/ 22.40 GFLOPS | Progress: (8/20) | 7.94 s
-[Task 6/25] Current/Best: 12.81/ 22.40 GFLOPS | Progress: (12/20) | 11.79 s
-[Task 6/25] Current/Best: 21.75/ 22.40 GFLOPS | Progress: (16/20) | 14.31 s
-[Task 6/25] Current/Best: 8.71/ 22.40 GFLOPS | Progress: (20/20) | 21.03 s Done.
+[Task 6/25] Current/Best: 10.06/ 14.91 GFLOPS | Progress: (4/20) | 5.45 s
+[Task 6/25] Current/Best: 17.97/ 18.44 GFLOPS | Progress: (8/20) | 7.62 s
+[Task 6/25] Current/Best: 14.04/ 18.44 GFLOPS | Progress: (12/20) | 10.73 s
+[Task 6/25] Current/Best: 16.02/ 18.44 GFLOPS | Progress: (16/20) | 14.00 s
+[Task 6/25] Current/Best: 9.38/ 18.44 GFLOPS | Progress: (20/20) | 17.28 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 10.84/ 17.35 GFLOPS | Progress: (4/20) | 4.96 s
-[Task 7/25] Current/Best: 9.21/ 18.13 GFLOPS | Progress: (8/20) | 7.72 s
-[Task 7/25] Current/Best: 3.15/ 18.13 GFLOPS | Progress: (12/20) | 11.13 s
-[Task 7/25] Current/Best: 16.75/ 18.13 GFLOPS | Progress: (16/20) | 13.38 s
-[Task 7/25] Current/Best: 15.28/ 18.13 GFLOPS | Progress: (20/20) | 17.14 s Done.
+[Task 7/25] Current/Best: 8.93/ 15.58 GFLOPS | Progress: (4/20) | 5.01 s
+[Task 7/25] Current/Best: 12.71/ 18.95 GFLOPS | Progress: (8/20) | 7.11 s
+[Task 7/25] Current/Best: 9.52/ 18.95 GFLOPS | Progress: (12/20) | 9.53 s
+[Task 7/25] Current/Best: 13.07/ 18.95 GFLOPS | Progress: (16/20) | 11.72 s
+[Task 7/25] Current/Best: 18.18/ 18.95 GFLOPS | Progress: (20/20) | 14.14 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 11.89/ 11.89 GFLOPS | Progress: (4/20) | 6.03 s
-[Task 8/25] Current/Best: 8.34/ 18.27 GFLOPS | Progress: (8/20) | 9.62 s
-[Task 8/25] Current/Best: 17.71/ 18.27 GFLOPS | Progress: (12/20) | 12.19 s
-[Task 8/25] Current/Best: 17.72/ 18.27 GFLOPS | Progress: (16/20) | 14.67 s
-[Task 8/25] Current/Best: 5.14/ 18.27 GFLOPS | Progress: (20/20) | 17.01 s Done.
+[Task 8/25] Current/Best: 11.98/ 13.54 GFLOPS | Progress: (4/20) | 5.91 s
+[Task 8/25] Current/Best: 10.77/ 19.07 GFLOPS | Progress: (8/20) | 8.21 s
+[Task 8/25] Current/Best: 14.32/ 19.07 GFLOPS | Progress: (12/20) | 11.78 s
+[Task 8/25] Current/Best: 7.49/ 20.53 GFLOPS | Progress: (16/20) | 15.39 s
+[Task 8/25] Current/Best: 18.66/ 20.53 GFLOPS | Progress: (20/20) | 18.22 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 12.04/ 22.76 GFLOPS | Progress: (4/20) | 5.41 s
-[Task 9/25] Current/Best: 11.45/ 22.76 GFLOPS | Progress: (8/20) | 8.32 s
-[Task 9/25] Current/Best: 6.30/ 22.76 GFLOPS | Progress: (12/20) | 19.58 s
-[Task 9/25] Current/Best: 12.58/ 22.76 GFLOPS | Progress: (16/20) | 23.64 s
-[Task 9/25] Current/Best: 19.47/ 22.76 GFLOPS | Progress: (20/20) | 25.40 s Done.
+[Task 9/25] Current/Best: 6.47/ 17.99 GFLOPS | Progress: (4/20) | 6.43 s
+[Task 9/25] Current/Best: 12.95/ 22.44 GFLOPS | Progress: (8/20) | 8.21 s
+[Task 9/25] Current/Best: 5.97/ 22.44 GFLOPS | Progress: (12/20) | 19.46 s
+[Task 9/25] Current/Best: 6.55/ 22.44 GFLOPS | Progress: (16/20) | 30.66 s
+[Task 9/25] Current/Best: 5.34/ 22.44 GFLOPS | Progress: (20/20) | 33.82 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 5.31/ 15.38 GFLOPS | Progress: (4/20) | 4.36 s
-[Task 10/25] Current/Best: 9.11/ 15.38 GFLOPS | Progress: (8/20) | 6.71 s
-[Task 10/25] Current/Best: 6.18/ 18.24 GFLOPS | Progress: (12/20) | 8.49 s
-[Task 10/25] Current/Best: 2.69/ 18.24 GFLOPS | Progress: (16/20) | 10.56 s
-[Task 10/25] Current/Best: 19.21/ 19.23 GFLOPS | Progress: (20/20) | 12.42 s Done.
+[Task 10/25] Current/Best: 13.76/ 14.01 GFLOPS | Progress: (4/20) | 4.44 s
+[Task 10/25] Current/Best: 14.29/ 18.13 GFLOPS | Progress: (8/20) | 6.16 s
+[Task 10/25] Current/Best: 16.01/ 18.13 GFLOPS | Progress: (12/20) | 7.83 s
+[Task 10/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (16/20) | 11.11 s
+[Task 10/25] Current/Best: 16.43/ 18.28 GFLOPS | Progress: (20/20) | 13.57 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 21.27/ 21.27 GFLOPS | Progress: (4/20) | 5.21 s
-[Task 11/25] Current/Best: 21.14/ 21.27 GFLOPS | Progress: (8/20) | 7.62 s
-[Task 11/25] Current/Best: 14.79/ 21.84 GFLOPS | Progress: (12/20) | 9.59 s
-[Task 11/25] Current/Best: 9.33/ 21.84 GFLOPS | Progress: (16/20) | 11.91 s
-[Task 11/25] Current/Best: 8.00/ 21.84 GFLOPS | Progress: (20/20) | 14.40 s Done.
+[Task 11/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (4/20) | 6.22 s
+[Task 11/25] Current/Best: 13.08/ 19.44 GFLOPS | Progress: (8/20) | 8.85 s
+[Task 11/25] Current/Best: 17.50/ 20.51 GFLOPS | Progress: (12/20) | 11.23 s
+[Task 11/25] Current/Best: 16.40/ 20.51 GFLOPS | Progress: (16/20) | 14.07 s
+[Task 11/25] Current/Best: 10.03/ 20.51 GFLOPS | Progress: (20/20) | 17.04 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 18.73/ 18.73 GFLOPS | Progress: (4/20) | 5.30 s
-[Task 12/25] Current/Best: 9.04/ 18.73 GFLOPS | Progress: (8/20) | 9.92 s
-[Task 12/25] Current/Best: 11.18/ 18.73 GFLOPS | Progress: (12/20) | 15.76 s
-[Task 12/25] Current/Best: 6.80/ 18.73 GFLOPS | Progress: (16/20) | 18.12 s
-[Task 12/25] Current/Best: 5.81/ 18.93 GFLOPS | Progress: (20/20) | 20.85 s Done.
+[Task 12/25] Current/Best: 5.20/ 14.34 GFLOPS | Progress: (4/20) | 8.34 s
+[Task 12/25] Current/Best: 12.25/ 18.68 GFLOPS | Progress: (8/20) | 10.57 s
+[Task 12/25] Current/Best: 15.83/ 18.68 GFLOPS | Progress: (12/20) | 14.68 s
+[Task 12/25] Current/Best: 14.91/ 18.68 GFLOPS | Progress: (16/20) | 19.00 s
+[Task 12/25] Current/Best: 5.01/ 18.68 GFLOPS | Progress: (20/20) | 21.97 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 10.18/ 19.71 GFLOPS | Progress: (4/20) | 4.96 s
-[Task 13/25] Current/Best: 18.15/ 19.71 GFLOPS | Progress: (8/20) | 7.65 s
-[Task 13/25] Current/Best: 10.01/ 20.72 GFLOPS | Progress: (12/20) | 9.88 s
-[Task 13/25] Current/Best: 5.25/ 20.91 GFLOPS | Progress: (16/20) | 13.30 s
-[Task 13/25] Current/Best: 8.66/ 20.91 GFLOPS | Progress: (20/20) | 16.88 s Done.
+[Task 13/25] Current/Best: 8.83/ 20.26 GFLOPS | Progress: (4/20) | 5.28 s
+[Task 13/25] Current/Best: 7.66/ 20.26 GFLOPS | Progress: (8/20) | 9.20 s
+[Task 13/25] Current/Best: 16.95/ 20.26 GFLOPS | Progress: (12/20) | 11.46 s
+[Task 13/25] Current/Best: 5.89/ 20.26 GFLOPS | Progress: (16/20) | 14.96 s
+[Task 13/25] Current/Best: 9.93/ 20.26 GFLOPS | Progress: (20/20) | 17.34 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.32/ 16.06 GFLOPS | Progress: (4/20) | 4.44 s
-[Task 14/25] Current/Best: 10.78/ 16.53 GFLOPS | Progress: (8/20) | 7.87 s
-[Task 14/25] Current/Best: 9.55/ 16.53 GFLOPS | Progress: (12/20) | 12.47 s
-[Task 14/25] Current/Best: 16.60/ 16.60 GFLOPS | Progress: (16/20) | 14.94 s
-[Task 14/25] Current/Best: 13.10/ 19.01 GFLOPS | Progress: (20/20) | 17.15 s
+[Task 14/25] Current/Best: 4.53/ 8.90 GFLOPS | Progress: (4/20) | 6.16 s
+[Task 14/25] Current/Best: 16.69/ 16.69 GFLOPS | Progress: (8/20) | 10.05 s
+[Task 14/25] Current/Best: 15.77/ 16.69 GFLOPS | Progress: (12/20) | 12.46 s
+[Task 14/25] Current/Best: 10.06/ 16.69 GFLOPS | Progress: (16/20) | 16.70 s
+[Task 14/25] Current/Best: 14.59/ 16.69 GFLOPS | Progress: (20/20) | 19.04 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 10.10/ 18.27 GFLOPS | Progress: (4/20) | 8.22 s
-[Task 15/25] Current/Best: 11.62/ 18.27 GFLOPS | Progress: (8/20) | 12.92 s
-[Task 15/25] Current/Best: 10.70/ 18.27 GFLOPS | Progress: (12/20) | 15.67 s
-[Task 15/25] Current/Best: 9.47/ 18.27 GFLOPS | Progress: (16/20) | 21.09 s
-[Task 15/25] Current/Best: 6.16/ 21.83 GFLOPS | Progress: (20/20) | 23.16 s Done.
+[Task 15/25] Current/Best: 11.70/ 12.77 GFLOPS | Progress: (4/20) | 8.39 s
+[Task 15/25] Current/Best: 12.21/ 20.88 GFLOPS | Progress: (8/20) | 10.21 s
+[Task 15/25] Current/Best: 20.64/ 20.88 GFLOPS | Progress: (12/20) | 12.20 s
+[Task 15/25] Current/Best: 11.02/ 20.88 GFLOPS | Progress: (16/20) | 16.83 s
+[Task 15/25] Current/Best: 13.87/ 20.88 GFLOPS | Progress: (20/20) | 19.63 s Done.
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 10.76/ 21.46 GFLOPS | Progress: (4/20) | 5.20 s
-[Task 16/25] Current/Best: 4.94/ 21.46 GFLOPS | Progress: (8/20) | 7.18 s
-[Task 16/25] Current/Best: 15.88/ 21.46 GFLOPS | Progress: (12/20) | 8.68 s
-[Task 16/25] Current/Best: 17.21/ 21.46 GFLOPS | Progress: (16/20) | 10.93 s
-[Task 16/25] Current/Best: 4.92/ 21.46 GFLOPS | Progress: (20/20) | 12.98 s Done.
+[Task 16/25] Current/Best: 19.02/ 19.02 GFLOPS | Progress: (4/20) | 4.34 s
+[Task 16/25] Current/Best: 14.77/ 19.02 GFLOPS | Progress: (8/20) | 6.07 s
+[Task 16/25] Current/Best: 10.90/ 19.02 GFLOPS | Progress: (12/20) | 7.84 s
+[Task 16/25] Current/Best: 13.50/ 19.02 GFLOPS | Progress: (16/20) | 9.41 s
+[Task 16/25] Current/Best: 7.25/ 20.38 GFLOPS | Progress: (20/20) | 11.02 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 6.14/ 15.87 GFLOPS | Progress: (4/20) | 5.67 s
-[Task 17/25] Current/Best: 8.93/ 16.42 GFLOPS | Progress: (8/20) | 8.21 s
-[Task 17/25] Current/Best: 21.73/ 21.73 GFLOPS | Progress: (12/20) | 12.55 s
-[Task 17/25] Current/Best: 7.63/ 21.73 GFLOPS | Progress: (16/20) | 16.56 s
-[Task 17/25] Current/Best: 18.23/ 22.66 GFLOPS | Progress: (20/20) | 18.84 s Done.
+[Task 17/25] Current/Best: 19.23/ 19.23 GFLOPS | Progress: (4/20) | 5.26 s
+[Task 17/25] Current/Best: 12.18/ 20.77 GFLOPS | Progress: (8/20) | 7.29 s
+[Task 17/25] Current/Best: 9.29/ 20.77 GFLOPS | Progress: (12/20) | 11.75 s
+[Task 17/25] Current/Best: 8.07/ 20.77 GFLOPS | Progress: (16/20) | 14.20 s
+[Task 17/25] Current/Best: 11.83/ 20.77 GFLOPS | Progress: (20/20) | 16.57 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 12.18/ 12.66 GFLOPS | Progress: (4/20) | 6.27 s
-[Task 18/25] Current/Best: 5.07/ 19.48 GFLOPS | Progress: (8/20) | 12.16 s
-[Task 18/25] Current/Best: 23.11/ 23.11 GFLOPS | Progress: (12/20) | 14.70 s
-[Task 18/25] Current/Best: 19.40/ 23.11 GFLOPS | Progress: (16/20) | 18.63 s
-[Task 18/25] Current/Best: 13.82/ 23.11 GFLOPS | Progress: (20/20) | 21.68 s Done.
+[Task 18/25] Current/Best: 11.52/ 15.18 GFLOPS | Progress: (4/20) | 6.03 s
+[Task 18/25] Current/Best: 10.12/ 16.20 GFLOPS | Progress: (8/20) | 9.90 s
+[Task 18/25] Current/Best: 15.59/ 16.20 GFLOPS | Progress: (12/20) | 12.93 s
+[Task 18/25] Current/Best: 16.50/ 16.50 GFLOPS | Progress: (16/20) | 14.94 s
+[Task 18/25] Current/Best: 13.42/ 16.50 GFLOPS | Progress: (20/20) | 18.13 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 11.78/ 11.91 GFLOPS | Progress: (4/20) | 8.06 s
-[Task 19/25] Current/Best: 16.22/ 16.22 GFLOPS | Progress: (8/20) | 10.95 s
-[Task 19/25] Current/Best: 6.50/ 20.65 GFLOPS | Progress: (12/20) | 14.07 s
-[Task 19/25] Current/Best: 10.52/ 20.65 GFLOPS | Progress: (16/20) | 17.43 s
-[Task 19/25] Current/Best: 8.81/ 20.65 GFLOPS | Progress: (20/20) | 21.80 s Done.
+[Task 19/25] Current/Best: 11.56/ 18.04 GFLOPS | Progress: (4/20) | 6.83 s
+[Task 19/25] Current/Best: 8.24/ 18.04 GFLOPS | Progress: (8/20) | 10.89 s
+[Task 19/25] Current/Best: 7.08/ 18.04 GFLOPS | Progress: (12/20) | 15.86 s
+[Task 19/25] Current/Best: 22.32/ 22.32 GFLOPS | Progress: (16/20) | 19.86 s
+[Task 19/25] Current/Best: 6.93/ 22.32 GFLOPS | Progress: (20/20) | 24.45 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.65/ 18.30 GFLOPS | Progress: (4/20) | 5.59 s Done.
-
-[Task 20/25] Current/Best: 13.79/ 18.30 GFLOPS | Progress: (8/20) | 9.33 s
-[Task 20/25] Current/Best: 8.82/ 18.30 GFLOPS | Progress: (12/20) | 12.10 s
-[Task 20/25] Current/Best: 6.73/ 18.30 GFLOPS | Progress: (16/20) | 15.76 s
-[Task 20/25] Current/Best: 14.32/ 18.30 GFLOPS | Progress: (20/20) | 18.22 s
-[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 14.74/ 17.01 GFLOPS | Progress: (4/20) | 5.10 s
-[Task 21/25] Current/Best: 6.55/ 17.01 GFLOPS | Progress: (8/20) | 7.24 s
-[Task 21/25] Current/Best: 5.14/ 17.01 GFLOPS | Progress: (12/20) | 11.32 s
-[Task 21/25] Current/Best: 10.54/ 17.01 GFLOPS | Progress: (16/20) | 13.88 s
-[Task 21/25] Current/Best: 4.67/ 17.01 GFLOPS | Progress: (20/20) | 16.65 s
-[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+[Task 20/25] Current/Best: 19.68/ 19.68 GFLOPS | Progress: (4/20) | 5.32 s
+[Task 20/25] Current/Best: 18.27/ 19.68 GFLOPS | Progress: (8/20) | 8.65 s
+[Task 20/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (12/20) | 12.29 s
+[Task 20/25] Current/Best: 12.63/ 21.22 GFLOPS | Progress: (16/20) | 14.78 s
+[Task 20/25] Current/Best: 10.56/ 21.22 GFLOPS | Progress: (20/20) | 16.84 s
+[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-[Task 22/25] Current/Best: 16.08/ 16.08 GFLOPS | Progress: (4/20) | 5.22 s
-[Task 22/25] Current/Best: 10.30/ 17.25 GFLOPS | Progress: (8/20) | 10.34 s
-[Task 22/25] Current/Best: 3.08/ 17.33 GFLOPS | Progress: (12/20) | 12.42 s
-[Task 22/25] Current/Best: 9.54/ 17.33 GFLOPS | Progress: (16/20) | 14.56 s
-[Task 22/25] Current/Best: 16.10/ 17.33 GFLOPS | Progress: (20/20) | 16.60 s Done.
+[Task 21/25] Current/Best: 7.43/ 20.26 GFLOPS | Progress: (4/20) | 5.87 s
+[Task 21/25] Current/Best: 6.67/ 20.26 GFLOPS | Progress: (8/20) | 8.93 s
+[Task 21/25] Current/Best: 9.89/ 20.26 GFLOPS | Progress: (12/20) | 15.76 s
+[Task 21/25] Current/Best: 2.26/ 20.26 GFLOPS | Progress: (16/20) | 18.26 s
+[Task 21/25] Current/Best: 5.38/ 20.26 GFLOPS | Progress: (20/20) | 21.50 s
+[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 22/25] Current/Best: 13.21/ 19.74 GFLOPS | Progress: (4/20) | 5.25 s
+[Task 22/25] Current/Best: 9.05/ 19.74 GFLOPS | Progress: (8/20) | 7.49 s
+[Task 22/25] Current/Best: 10.63/ 19.74 GFLOPS | Progress: (12/20) | 9.99 s
+[Task 22/25] Current/Best: 10.57/ 19.74 GFLOPS | Progress: (16/20) | 11.64 s
+[Task 22/25] Current/Best: 10.60/ 19.74 GFLOPS | Progress: (20/20) | 13.31 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 6.57/ 12.98 GFLOPS | Progress: (4/20) | 5.26 s
-[Task 23/25] Current/Best: 12.82/ 12.98 GFLOPS | Progress: (8/20) | 8.97 s
-[Task 23/25] Current/Best: 12.04/ 17.82 GFLOPS | Progress: (12/20) | 14.32 s
-[Task 23/25] Current/Best: 18.39/ 21.89 GFLOPS | Progress: (16/20) | 16.85 s
-[Task 23/25] Current/Best: 17.76/ 21.89 GFLOPS | Progress: (20/20) | 20.06 s Done.
+[Task 23/25] Current/Best: 6.46/ 14.39 GFLOPS | Progress: (4/20) | 5.74 s
+[Task 23/25] Current/Best: 11.50/ 17.95 GFLOPS | Progress: (8/20) | 8.92 s
+[Task 23/25] Current/Best: 10.83/ 17.95 GFLOPS | Progress: (12/20) | 11.39 s
+[Task 23/25] Current/Best: 5.26/ 17.95 GFLOPS | Progress: (16/20) | 17.73 s
+[Task 23/25] Current/Best: 12.14/ 17.95 GFLOPS | Progress: (20/20) | 20.97 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 4.53/ 9.04 GFLOPS | Progress: (4/20) | 13.45 s
-[Task 24/25] Current/Best: 3.27/ 9.04 GFLOPS | Progress: (8/20) | 24.11 s
-[Task 24/25] Current/Best: 5.69/ 9.04 GFLOPS | Progress: (12/20) | 35.10 s
-[Task 24/25] Current/Best: 3.57/ 9.04 GFLOPS | Progress: (16/20) | 46.06 s
-[Task 24/25] Current/Best: 9.68/ 9.68 GFLOPS | Progress: (20/20) | 57.01 s
-[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
-[Task 25/25] Current/Best: 2.87/ 9.30 GFLOPS | Progress: (4/20) | 5.11 s
-[Task 25/25] Current/Best: 9.03/ 9.30 GFLOPS | Progress: (8/20) | 6.76 s
-[Task 25/25] Current/Best: 7.52/ 9.30 GFLOPS | Progress: (12/20) | 17.73 s
-[Task 25/25] Current/Best: 1.55/ 9.30 GFLOPS | Progress: (16/20) | 28.74 s
-[Task 25/25] Current/Best: 8.06/ 9.30 GFLOPS | Progress: (20/20) | 33.55 s
+[Task 24/25] Current/Best: 3.73/ 3.73 GFLOPS | Progress: (4/20) | 13.39 s
+[Task 24/25] Current/Best: 2.96/ 10.30 GFLOPS | Progress: (8/20) | 21.73 s
+[Task 24/25] Current/Best: 3.68/ 10.30 GFLOPS | Progress: (12/20) | 32.67 s
+[Task 24/25] Current/Best: 4.95/ 10.30 GFLOPS | Progress: (16/20) | 35.35 s
+[Task 24/25] Current/Best: 10.07/ 10.30 GFLOPS | Progress: (20/20) | 38.24 s
+[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
+[Task 25/25] Current/Best: 5.87/ 5.87 GFLOPS | Progress: (4/20) | 7.09 s
+[Task 25/25] Current/Best: 8.44/ 9.36 GFLOPS | Progress: (8/20) | 18.02 s
+[Task 25/25] Current/Best: 8.33/ 9.36 GFLOPS | Progress: (12/20) | 28.70 s
+[Task 25/25] Current/Best: 1.55/ 9.36 GFLOPS | Progress: (16/20) | 31.27 s
+[Task 25/25] Current/Best: 3.03/ 9.36 GFLOPS | Progress: (20/20) | 32.74 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -943,8 +941,8 @@ 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
@@ -981,8 +979,8 @@ 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': 409.8005634200035, 'median': 409.5368252500066, 'std': 1.0931895077648477}
-unoptimized: {'mean': 515.2758335699855, 'median': 515.3482555999744, 'std': 1.2878188221012696}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 422.1741954800041, 'median': 420.3180206499951, 'std': 3.051434370680484}
+unoptimized: {'mean': 512.0541001199969, 'median': 511.61899980000385, 'std': 1.4801657422214596}
</pre></div>
</div>
</div>
@@ -996,7 +994,7 @@ 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 20.754 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 54.210 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 fcd118623d..8529d1ffc8 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -538,7 +538,7 @@ 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>1.371e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.332e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index e063e06b69..e42639fb7d 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -515,7 +515,7 @@ 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, 0x1395f1a0)), stage(b, placeholder(b, 0x1010b1d0)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attr [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x11a66320)), stage(b, placeholder(b, 0x11ab8d90)), 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 76b723d62f..2c9cd6009b 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:40.372</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:24.129</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,46 +349,46 @@
</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>12:20.754</p></td>
+<td><p>11:54.210</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>01:19.728</p></td>
+<td><p>01:31.356</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>00:58.915</p></td>
+<td><p>01:00.946</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:36.999</p></td>
+<td><p>00:36.440</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:22.318</p></td>
+<td><p>00:18.545</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<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>00:00.869</p></td>
+<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>00:01.619</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<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>00:00.615</p></td>
+<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>00:00.853</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>00:00.172</p></td>
+<td><p>00:00.161</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>
<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="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 91ca4489ef..69d81e4ffb 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -608,7 +608,7 @@ compile and run this new schedule with the parallel operation applied:</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd_parallel</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"parallel"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.h [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000007
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallel: 0.000013
</pre></div>
</div>
</div>
@@ -647,7 +647,7 @@ 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: 0.000025
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector: 0.000035
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -687,10 +687,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 6.773159993826994e-06 1.0
- naive 6.8217e-06 1.0071665228958486
-parallel 6.961499999999999e-06 1.0278068148906356
- vector 2.4627900000000002e-05 3.6361019114336117
+ numpy 7.371080000666552e-06 1.0
+ naive 7.4293e-06 1.0078984354162732
+parallel 1.3010499999999999e-05 1.7650737746467933
+ vector 3.4542600000000004e-05 4.68623322455819
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1006,7 +1006,7 @@ 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: 0.019323
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017841
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1047,7 +1047,7 @@ 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: 3.212878
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.420906
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1111,7 +1111,7 @@ 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: 0.320971
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.292330
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1160,7 +1160,7 @@ 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: 0.347963
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.328753
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1209,7 +1209,7 @@ 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: 0.116840
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.117951
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1279,7 +1279,7 @@ 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: 0.109135
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109251
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1345,7 +1345,7 @@ 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: 0.111038
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110578
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1402,7 +1402,7 @@ 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: 0.144915
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.145928
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1455,13 +1455,13 @@ 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 3.212877511 1.0
- blocking 0.3209708349 0.09990136063422432
- vectorization 0.3479628775 0.10830256563117385
-loop permutation 0.1168403039 0.036366249102236625
- array packing 0.10913453039999998 0.03396784658809857
- block caching 0.11103821089999999 0.034560362329356165
- parallelization 0.14491518390000002 0.04510448450146347
+ none 3.4209055244000006 1.0
+ blocking 0.2923301274 0.08545401950300055
+ vectorization 0.32875337849999997 0.0961012738162831
+loop permutation 0.1179507608 0.03447939732877821
+ array packing 0.10925069289999997 0.03193619119872118
+ block caching 0.1105783484 0.03232429180264911
+ parallelization 0.14592845110000002 0.04265784309421836
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1493,6 +1493,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.946 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>