You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/04/06 20:52:20 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@af39b3441d13e6a672ea7a079b727e11252d267a)
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 d59ba02065 deploying docs (apache/tvm@af39b3441d13e6a672ea7a079b727e11252d267a)
d59ba02065 is described below
commit d59ba02065374bbe9bb69e133c459a544697cf31
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Thu Apr 6 20:52:14 2023 +0000
deploying docs (apache/tvm@af39b3441d13e6a672ea7a079b727e11252d267a)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 322594 -> 343660 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23763 -> 23847 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 2 +-
.../deploy_model_on_adreno_tvmc.rst.txt | 2 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 22 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1757 ++++++++++----------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 89 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 72 +-
.../work_with_microtvm/micro_autotune.rst.txt | 18 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 14 +-
.../work_with_relay/sg_execution_times.rst.txt | 10 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 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 | 11 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 15 +-
docs/how_to/compile_models/from_pytorch.html | 12 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_adreno.html | 2 +-
.../deploy_models/deploy_model_on_adreno_tvmc.html | 31 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 59 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 37 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1757 ++++++++++----------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 89 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 72 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 18 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 5 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 14 +-
.../how_to/work_with_relay/sg_execution_times.html | 10 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
.../doxygen/classtvm_1_1SEqualReducer-members.html | 31 +-
.../api/doxygen/classtvm_1_1SEqualReducer.html | 190 ++-
.../classtvm_1_1SEqualReducer__coll__graph.svg | 2 +-
docs/reference/api/doxygen/functions_func_o.html | 36 +-
docs/reference/api/doxygen/functions_o.html | 14 +-
docs/reference/api/doxygen/ir_2expr_8h_source.html | 2 +-
docs/reference/api/doxygen/ir_2type_8h_source.html | 2 +-
.../api/doxygen/relay_2base_8h_source.html | 2 +-
docs/reference/api/doxygen/search/all_10.js | 2 +-
docs/reference/api/doxygen/search/functions_f.js | 2 +-
.../api/doxygen/structural__equal_8h_source.html | 18 +-
docs/reference/api/doxygen/var_8h_source.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
docs/reference/api/typedoc/classes/instance.html | 58 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
.../api/typedoc/classes/runtimecontext.html | 22 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
docs/reference/api/typedoc/classes/tvmarray.html | 16 +-
docs/reference/api/typedoc/classes/tvmobject.html | 12 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 124 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 272 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 18 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
141 files changed, 2958 insertions(+), 2922 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 4241e968ab..4f3246f529 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 b902e38929..3ef5dcacc2 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 e7537d1e19..947ed29c99 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -318,7 +318,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.950 seconds)
+ **Total running time of the script:** ( 1 minutes 25.696 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index e6aaff96a1..dd28483094 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.zipf99c1b85-012b-4980-be7f-9b3aefbd2168 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip71cd500c-0843-4e19-9c7f-d6fc3160bf08 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 504a6759d6..18f917b08a 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]
15%|#5 | 6.33M/41.5M [00:00<00:00, 49.3MB/s]
27%|##6 | 11.0M/41.5M [00:00<00:01, 30.5MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 31.1MB/s]
42%|####2 | 17.5M/41.5M [00:00<00:00, 29.9MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 34.1MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.7MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 30.7MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 33.7MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 36.2MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 33.3MB/s]
42%|####2 | 17.5M/41.5M [00:00<00:00, 29.1MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 32.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.1MB/s]
92%|#########2| 38.3M/41.5M [00:01<00:00, 39.2MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 36.7MB/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 b162d491a9..db3ab4805b 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -101,7 +101,7 @@ Load a pretrained PyTorch model
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 56.6MB/s]
36%|###5 | 16.0M/44.7M [00:00<00:00, 61.3MB/s]
72%|#######1 | 32.0M/44.7M [00:00<00:00, 86.3MB/s]
90%|########9 | 40.1M/44.7M [00:00<00:00, 84.4MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 70.7MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#7 | 7.99M/44.7M [00:00<00:00, 76.7MB/s]
34%|###4 | 15.3M/44.7M [00:00<00:00, 68.4MB/s]
49%|####8 | 21.9M/44.7M [00:00<00:00, 58.1MB/s]
67%|######6 | 29.8M/44.7M [00:00<00:00, 66.5MB/s]
82%|########2 | 36.7M/44.7M [00:00<00:00, 68.4MB/s]
97%|#########7| 43.4M/44.7M [00:00<00:00, 65.6MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 63.3MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index b28a39f08d..bb02a7236d 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -430,7 +430,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.011 seconds)
+ **Total running time of the script:** ( 1 minutes 36.234 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 3781a510a5..10f9033ddf 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
=================
-**06:56.534** total execution time for **how_to_compile_models** files:
+**07:13.150** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:33.011 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:36.234 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:22.950 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:25.696 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:56.989 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:59.848 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.695 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:40.261 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:32.820 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:34.679 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.848 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:31.763 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:28.464 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:28.941 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:26.885 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:27.505 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:23.139 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:25.368 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.733 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.854 | 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 65a93874fe..5e6dc5abb6 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -637,7 +637,7 @@ well as provides information about the model's performance
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2558.9181 2558.5411 2562.7793 2557.7647 1.3580
+ 2752.1900 2751.4499 2755.9287 2749.9418 2.1244
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
index f927f12ad7..b215ea737c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno_tvmc.rst.txt
@@ -127,7 +127,7 @@ Make a Keras Resnet50 Model
.. code-block:: none
Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
-
8192/102967424 [..............................] - ETA: 0s
7643136/102967424 [=>............................] - ETA: 0s
12689408/102967424 [==>...........................] - ETA: 0s
17350656/102967424 [====>.........................] - ETA: 0s
22708224/102967424 [=====>........................] - ETA: 0s
25157632/102967424 [======>.......................] - ETA: 0s
30605312/102967424 [=======>......................] - ETA: 0s
38526976/102967424 [==========>...................] - ETA: 0s
40189952/102967424 [==========>...................] - ETA: 0s
44130304/102967424 [===========>..................] - ETA: 0s
52625408/102967424 [==============>...............] - ETA: 0s
64823296/102967424 [=================>............] - ETA: 0s
67313664/102967424 [==================>...........] - ETA: 0s
74899456/102967424 [====================>.........] - ETA: 0s
79986688/102967424 [======================>.......] - ETA: 0s
83886080/102967424 [=======================>......] -
ETA: 0s
89325568/102967424 [=========================>....] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
100646912/102967424 [============================>.] - ETA: 0s
102850560/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
+
8192/102967424 [..............................] - ETA: 0s
8380416/102967424 [=>............................] - ETA: 0s
16769024/102967424 [===>..........................] - ETA: 0s
16908288/102967424 [===>..........................] - ETA: 1s
25157632/102967424 [======>.......................] - ETA: 0s
33546240/102967424 [========>.....................] - ETA: 0s
38191104/102967424 [==========>...................] - ETA: 0s
45080576/102967424 [============>.................] - ETA: 0s
50323456/102967424 [=============>................] - ETA: 0s
58654720/102967424 [================>.............] - ETA: 0s
63725568/102967424 [=================>............] - ETA: 0s
67100672/102967424 [==================>...........] - ETA: 0s
72540160/102967424 [====================>.........] - ETA: 0s
75202560/102967424 [====================>.........] - ETA: 0s
84508672/102967424 [=======================>......] - ETA: 0s
86073344/102967424 [========================>.....] -
ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 1b4f6c13a2..a4fc63ffb0 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)
- 15.7801 15.7841 15.9218 15.6153 0.0960
+ 17.1162 17.1192 17.5817 16.3485 0.3853
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 0febd6ba83..61e792838b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -130,7 +130,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=MaskRCNN_ResNet50_FPN_Weights.COCO_V1`. You can also use `weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT` to get the most up-to-date weights.
warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
4%|3 | 6.30M/170M [00:00<00:02, 60.4MB/s]
8%|7 | 13.0M/170M [00:00<00:02, 65.7MB/s]
11%|#1 | 19.2M/170M [00:00<00:03, 50.1MB/s]
14%|#4 | 24.3M/170M [00:00<00:03, 47.1MB/s]
18%|#7 | 30.3M/170M [00:00<00:02, 51.5MB/s]
22%|##1 | 37.3M/170M [00:00<00:02, 58.1MB/s]
25%|##5 | 43.1M/170M [00:00<00:02, 58.7MB/s]
29%|##8 | 48.9M/170M [00:00<00:02, 46.7MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 52.3MB/s]
37%|###6 | 62.3M/170M [00:01<00:02, 49.1MB/s]
40%|###9 | 67.3M/170M [00:01<00:02, 48.6MB/s]
42%|####2 | 72.1M/170M [00:01<00:02, 46.1MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 52.1MB/s]
51%|##### | 86.3M/170M [00:01<00:01, 52.3MB/s]
54%|#####3 | 91.4M/170M [00:01<00:01, 49.1MB/s]
57%|#####6 | 96.1M/170M [00:02<00:01, 44.3MB/s]
61%|###### | 103M/170M [00:02<00:01, 51.4MB/s
]
64%|######3 | 108M/170M [00:02<00:01, 49.8MB/s]
67%|######6 | 113M/170M [00:02<00:01, 48.1MB/s]
69%|######9 | 118M/170M [00:02<00:01, 48.2MB/s]
72%|#######2 | 122M/170M [00:02<00:01, 38.7MB/s]
75%|#######5 | 128M/170M [00:02<00:01, 38.4MB/s]
80%|######## | 136M/170M [00:02<00:00, 43.9MB/s]
85%|########4 | 144M/170M [00:03<00:00, 48.2MB/s]
89%|########9 | 152M/170M [00:03<00:00, 47.2MB/s]
94%|#########4| 160M/170M [00:03<00:00, 49.8MB/s]
99%|#########8| 168M/170M [00:03<00:00, 56.9MB/s]
100%|##########| 170M/170M [00:03<00:00, 50.3MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:04, 42.3MB/s]
8%|8 | 14.3M/170M [00:00<00:03, 46.8MB/s]
11%|#1 | 18.9M/170M [00:00<00:03, 44.7MB/s]
14%|#4 | 24.0M/170M [00:00<00:03, 43.7MB/s]
18%|#7 | 30.3M/170M [00:00<00:03, 39.9MB/s]
20%|## | 34.2M/170M [00:00<00:03, 35.6MB/s]
24%|##3 | 40.0M/170M [00:01<00:03, 41.6MB/s]
28%|##8 | 48.0M/170M [00:01<00:02, 51.4MB/s]
33%|###2 | 56.0M/170M [00:01<00:02, 46.1MB/s]
36%|###5 | 60.8M/170M [00:01<00:02, 43.1MB/s]
38%|###8 | 65.1M/170M [00:01<00:04, 25.6MB/s]
42%|####2 | 72.0M/170M [00:02<00:03, 27.2MB/s]
46%|####6 | 78.3M/170M [00:02<00:02, 32.2MB/s]
48%|####8 | 82.1M/170M [00:02<00:02, 33.1MB/s]
52%|#####1 | 88.0M/170M [00:02<00:02, 33.8MB/s]
56%|#####5 | 94.3M/170M [00:02<00:02, 35.5MB/s]
58%|#####7 | 98.0M/170M [00:02<00:02, 30.1MB/
s]
61%|######1 | 104M/170M [00:03<00:02, 29.5MB/s]
66%|######5 | 112M/170M [00:03<00:01, 38.2MB/s]
71%|####### | 120M/170M [00:03<00:01, 41.3MB/s]
75%|#######5 | 128M/170M [00:03<00:00, 45.8MB/s]
79%|#######9 | 134M/170M [00:03<00:01, 34.3MB/s]
81%|########1 | 138M/170M [00:03<00:00, 34.2MB/s]
85%|########4 | 144M/170M [00:04<00:00, 34.8MB/s]
89%|########9 | 152M/170M [00:04<00:00, 38.7MB/s]
94%|#########3| 159M/170M [00:04<00:00, 45.8MB/s]
97%|#########6| 164M/170M [00:04<00:00, 41.7MB/s]
99%|#########9| 168M/170M [00:04<00:00, 39.0MB/s]
100%|##########| 170M/170M [00:04<00:00, 37.6MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 37.665 seconds)
+ **Total running time of the script:** ( 3 minutes 57.182 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 7868e5d5e0..781a0a8daf 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, 35.4MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 48.5MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 71.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 73.3MB/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)
- 90.3574 90.3433 90.8663 90.0979 0.1445
+ 90.8695 90.7012 99.6477 90.3184 1.0222
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 17.818 seconds)
+ **Total running time of the script:** ( 1 minutes 21.477 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 fad492c9f5..d426f28a5c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -423,7 +423,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.9266 120.9304 122.1458 119.3036 0.4708
+ 121.5235 121.4552 126.0071 120.5605 0.6347
@@ -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 40.023 seconds)
+ **Total running time of the script:** ( 2 minutes 32.560 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 f10a53d74a..a744a9dedf 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -257,7 +257,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 43.356 seconds)
+ **Total running time of the script:** ( 1 minutes 47.629 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 ed7a01025e..53f6f68317 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -170,7 +170,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
1%|1 | 1331/132723 [00:00<00:09, 13179.86KB/s]
3%|3 | 4243/132723 [00:00<00:05, 22480.18KB/s]
8%|7 | 10614/132723 [00:00<00:02, 41245.65KB/s]
15%|#4 | 19323/132723 [00:00<00:01, 59306.31KB/s]
21%|##1 | 28084/132723 [00:00<00:01, 69498.00KB/s]
28%|##7 | 36873/132723 [00:00<00:01, 75743.83KB/s]
35%|###4 | 45803/132723 [00:00<00:01, 80169.49KB/s]
41%|####1 | 54648/132723 [00:00<00:00, 82801.16KB/s]
48%|####7 | 63499/132723 [00:00<00:00, 84583.76KB/s]
55%|#####4 | 72437/132723 [00:01<00:00, 86060.90KB/s]
61%|######1 | 81299/132723 [00:01<00:00, 86834.87KB/s]
68%|######7 | 90111/132723 [00:01<00:00, 87224.18KB/s]
75%|#######4 | 98994/132723 [00:01<00:00, 87708.56KB/s]
81%|########1 | 107822/132723 [00:01<00:00, 87879.02KB/s]
88%|########7 | 116664/132723 [00:01<00:00, 88034.69KB/s]
95%|#########4
| 125468/132723 [00:01<00:00, 87954.46KB/s]
100%|##########| 132723/132723 [00:01<00:00, 78681.29KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
1%| | 1148/132723 [00:00<00:11, 11448.78KB/s]
3%|2 | 3736/132723 [00:00<00:06, 19809.98KB/s]
7%|7 | 9412/132723 [00:00<00:03, 36615.78KB/s]
13%|#3 | 17848/132723 [00:00<00:02, 55415.05KB/s]
20%|#9 | 26262/132723 [00:00<00:01, 65755.58KB/s]
26%|##6 | 34784/132723 [00:00<00:01, 72365.04KB/s]
33%|###2 | 43328/132723 [00:00<00:01, 76634.94KB/s]
39%|###9 | 51894/132723 [00:00<00:01, 79504.00KB/s]
45%|####5 | 60366/132723 [00:00<00:00, 81131.30KB/s]
52%|#####1 | 68871/132723 [00:01<00:00, 82338.35KB/s]
58%|#####8 | 77436/132723 [00:01<00:00, 83348.29KB/s]
65%|######4 | 85772/132723 [00:01<00:00, 69368.04KB/s]
71%|#######1 | 94326/132723 [00:01<00:00, 73661.32KB/s]
77%|#######6 | 102024/132723 [00:01<00:00, 55606.34KB/s]
83%|########3 | 110551/132723 [00:01<00:00, 62325.90KB/s]
89%|########8 |
117599/132723 [00:01<00:00, 63411.43KB/s]
95%|#########4| 126029/132723 [00:01<00:00, 68760.21KB/s]
100%|##########| 132723/132723 [00:01<00:00, 67112.08KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 59.144 seconds)
+ **Total running time of the script:** ( 4 minutes 10.919 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 def5abe5ac..dab91814ae 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
Computation times
=================
-**16:47.218** total execution time for **how_to_deploy_models** files:
+**17:28.304** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:59.144 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 04:10.919 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:37.665 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:57.182 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:40.023 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:32.560 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:43.356 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:47.629 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:17.818 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:21.477 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:55.481 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:59.077 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:52.112 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno_tvmc.py` (``deploy_model_on_adreno_tvmc.py``) | 00:53.901 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:43.673 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:46.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:29.292 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:30.070 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:28.649 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:29.432 | 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 9a453c84e8..ccf1cb3f22 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.zip44b787e6-68dc-44b3-ba48-7ecf045ac893 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip7636ec96-a624-4e9f-8b4e-c1e7120f818b 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 a98d55c55b..477e0a9035 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:55.245** total execution time for **how_to_extend_tvm** files:
+**00:57.915** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:51.380 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:53.840 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.784 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.925 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.074 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.143 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :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 673250fb57..c8ea53a95d 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: 23061us [23061us] (48.72%; 48.72%)
- FoldScaleAxis: 24273us [10us] (51.28%; 51.28%)
- FoldConstant: 24264us [1756us] (51.26%; 99.96%)
- InferType: 22507us [22507us] (47.55%; 92.76%)
+ InferType: 23476us [23476us] (48.28%; 48.28%)
+ FoldScaleAxis: 25152us [9us] (51.72%; 51.72%)
+ FoldConstant: 25143us [1770us] (51.70%; 99.96%)
+ InferType: 23373us [23373us] (48.06%; 92.96%)
@@ -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: 22352us [22352us] (47.49%; 47.49%)
- FoldScaleAxis: 24719us [7us] (52.51%; 52.51%)
- FoldConstant: 24712us [1821us] (52.50%; 99.97%)
- InferType: 22891us [22891us] (48.63%; 92.63%)
+ InferType: 22887us [22887us] (48.07%; 48.07%)
+ FoldScaleAxis: 24728us [8us] (51.93%; 51.93%)
+ FoldConstant: 24721us [1868us] (51.92%; 99.97%)
+ InferType: 22853us [22853us] (48.00%; 92.44%)
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 23e0d58fa5..b9278263c6 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: 34.283519 ms
+ Convolution: 53.515617 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 e499428f14..91b535310c 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -598,7 +598,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 11.150541 ms
+ conv2d with tensor core: 12.236822 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 94ba234059..247ab85cc8 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: 0.018940
- Baseline: 3.198221
+ Numpy running time: 0.019959
+ Baseline: 3.471027
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.290675
+ Opt1: 0.339590
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.339132
+ Opt2: 0.359948
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118303
+ Opt3: 0.145167
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110241
+ Opt4: 0.111442
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111996
+ Opt5: 0.113196
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.147561
+ Opt6: 0.149567
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 f76c5b53a2..2c316ad393 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.824** total execution time for **how_to_optimize_operators** files:
+**00:37.205** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.823 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.990 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.863 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:02.000 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.138 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.215 | 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 d8b2cf4f5f..1bc833d41f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**10:09.517** total execution time for **how_to_tune_with_autoscheduler** files:
+**10:38.302** 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``) | 06:13.990 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 06:33.263 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:43.127 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:47.091 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:11.538 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:14.351 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:32.857 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:34.063 | 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``) | 00:15.032 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:13.750 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:14.501 | 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 5d0d8334cf..cbb8a26dbc 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -243,500 +243,479 @@ cooperative fetching, unrolling and operator fusion.
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- blockIdx_x = T.launch_thread("blockIdx.x", 8)
- conv2d_nchw = T.allocate([28], "float32", "local")
- pad_temp_shared = T.allocate([1296], "float32", "shared")
- kernel_shared = T.allocate([9216], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 112)
- conv2d_nchw_1 = T.Buffer((196,), data=conv2d_nchw, scope="local", align=32)
+ blockIdx_x = T.launch_thread("blockIdx.x", 28)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([72], "float32", "shared")
+ kernel_shared = T.allocate([3072], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 64)
+ conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[14] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[15] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[16] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[17] = T.float32(0)
conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[18] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[19] = T.float32(0)
conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[20] = T.float32(0)
conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[21] = T.float32(0)
conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[22] = T.float32(0)
conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[23] = T.float32(0)
conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[24] = T.float32(0)
conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[25] = T.float32(0)
conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[26] = T.float32(0)
conv2d_nchw_1[13] = T.float32(0)
- conv2d_nchw_1[27] = T.float32(0)
- for rc_outer_outer in range(32):
- cse_var_2: T.int32 = rc_outer_outer * 784
- cse_var_1: T.int32 = rc_outer_outer * 144
+ for rc_outer_outer, ry_outer_outer in T.grid(64, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 72
+ cse_var_1: T.int32 = ry_outer_outer * 3
+ pad_temp_shared_1 = T.Buffer((72,), data=pad_temp_shared, scope="shared")
+ with T.launch_thread("threadIdx.x", 64) as threadIdx_x_1:
+ data_1 = T.Buffer((25088,), data=data.data)
+ if T.likely(threadIdx_x_1 < 18):
+ pad_temp_shared_1[threadIdx_x_1 * 4] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= threadIdx_x_1 * 4 % 9 and threadIdx_x_1 * 4 % 9 < 8, data_1[rc_outer_outer * 392 + threadIdx_x_1 * 4 // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + threadIdx_x_1 * 4 % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 18):
+ pad_temp_shared_1[threadIdx_x_1 * 4 + 1] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 1) % 9 and (threadIdx_x_1 * 4 + 1) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 1) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 1) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 18):
+ pad_temp_shared_1[threadIdx_x_1 * 4 + 2] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 2) % 9 and (threadIdx_x_1 * 4 + 2) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 2) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 2) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 18):
+ pad_temp_shared_1[threadIdx_x_1 * 4 + 3] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 3) % 9 and (threadIdx_x_1 * 4 + 3) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 3) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 3) % 9 - 8], T.float32(0))
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((1296,), 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] = 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[cse_var_2 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(9 <= (threadIdx_x_1 + 31) % 81 and (threadIdx_x_1 + 31) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 81 * 49 + (threadIdx_x_1 + 31) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(9 <= (threadIdx_x_1 + 62) % 81 and (threadIdx_x_1 + 62) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 81 * 49 + (threadIdx_x_1 + 62) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 336] = T.if_then_else(9 <= (threadIdx_x_1 + 12) % 81 and (threadIdx_x_1 + 12) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 336) // 81 * 49 + (threadIdx_x_1 + 12) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 448] = T.if_then_else(9 <= (threadIdx_x_1 + 43) % 81 and (threadIdx_x_1 + 43) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 448) // 81 * 49 + (threadIdx_x_1 + 43) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 560] = T.if_then_else(9 <= (threadIdx_x_1 + 74) % 81 and (threadIdx_x_1 + 74) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 560) // 81 * 49 + (threadIdx_x_1 + 74) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 672] = T.if_then_else(9 <= (threadIdx_x_1 + 24) % 81 and (threadIdx_x_1 + 24) % 81 < 72 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 672) // 81 * 49 + (threadIdx_x_1 + 24) % 81 // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(9 <= (threadIdx_x_1 + 55) % 81 and (threadIdx_x_1 + 55) % 81 < 72 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 81 * 49 + (threadIdx_x_1 + 55) % 81 // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 896] = T.if_then_else(9 <= (threadIdx_x_1 + 5) % 81 and (threadIdx_x_1 + 5) % 81 < 72 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 896) // 81 * 49 + (threadIdx_x_1 + 5) % 81 // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 1008] = T.if_then_else(1 <= (threadIdx_x_1 // 9 + 4) % 9 and (threadIdx_x_1 + 36) % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1008) // 81 * 49 + (threadIdx_x_1 // 9 + 4) % 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 1120] = T.if_then_else(9 <= (threadIdx_x_1 + 67) % 81 and (threadIdx_x_1 + 67) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1120) // 81 * 49 + (threadIdx_x_1 + 67) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- if T.likely(threadIdx_x_1 < 64):
- pad_temp_shared_1[threadIdx_x_1 + 1232] = T.if_then_else(threadIdx_x_1 < 55 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1232) // 81 * 49 + (threadIdx_x_1 + 17) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((9216,), 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, 112):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 112] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 112) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 224] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 224) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 336) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 448] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 448) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 560] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 560) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 672) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 784) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 896] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 896) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1008] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 32256]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1120] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1120) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1232] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1232) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1344] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1344) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1456] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1456) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1568) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1680] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1680) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1792] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1792) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1904] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1904) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2016] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 64512]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2128] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2128) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2240] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2240) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2352] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2352) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2464] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2464) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2576] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2576) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2688] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2688) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2800] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2800) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2912] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2912) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3024] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 96768]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3136] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3136) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3248] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3248) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3360] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3360) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3472] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3472) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3584] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3584) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3696] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3696) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3808] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3808) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3920] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3920) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4032] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 129024]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4144] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4144) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4256] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4256) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4368] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4368) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4480] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4480) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4592] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4592) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4704] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4704) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4816] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4816) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4928] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4928) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5040] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 161280]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5152] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5152) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5264] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5264) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5376] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5376) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5488] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5488) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5600] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5600) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5712] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5712) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5824] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5824) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5936] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5936) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6048] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 193536]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6160] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6160) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6272] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6272) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6384] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6384) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6496] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6496) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6608] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6608) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6720] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6720) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6832] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6832) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6944] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6944) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7056] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 225792]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7168] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7168) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7280] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7280) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7392] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7392) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7504] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7504) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7616] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7616) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7728] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7728) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7840] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7840) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7952] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7952) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8064] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 258048]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8176] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8176) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8288] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8288) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8400] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8400) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8512] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8512) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8624] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8624) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8736] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8736) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8848] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8848) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8960] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8960) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 9072] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 290304]
- with T.launch_thread(threadIdx_x_2, 112):
- if T.likely(threadIdx_x_2 < 32):
- kernel_shared_1[threadIdx_x_2 + 9184] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 9184) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 112]
- for rc_inner in range(16):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- for i1_inner, i2_inner in T.grid(2, 7):
- cse_var_3: T.int32 = i1_inner * 7 + i2_inner
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 64) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 64) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 128) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 128) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 192] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 36864]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 256) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 256) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 320) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 320) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 384] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 73728]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 448) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 448) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 512) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 512) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 576] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 110592]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 640) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 640) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 704) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 704) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 768] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 147456]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 832) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 832) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 896) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 896) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 960] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 184320]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1024) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1024) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1088) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1088) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1152] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 221184]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1216) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1216) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1280) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1280) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1344] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 258048]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1408) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1408) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1472) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1472) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1536] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 294912]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1600) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1600) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1664) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1664) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1728] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 331776]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1792) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1792) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1856) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1856) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1920] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 368640]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1984) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1984) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2048) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2048) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2112] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 405504]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2176) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2176) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2240) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2240) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2304] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 442368]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2368) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2368) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2432) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2432) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2496] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 479232]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2560) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2560) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2624) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2624) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2688] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 516096]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2752) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2752) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2816) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2816) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2880] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 552960]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2944) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2944) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 3008) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 3008) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 47]
+ for i1_inner, i3_inner in T.grid(2, 7):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 3136 + threadIdx_x // 7 * 98 + i1_inner * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[cse_var_3] + bias_1[blockIdx_x * 64 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 3136 + threadIdx_x // 7 * 98 + i1_inner * 49 + i2_inner * 7 + threadIdx_x % 7 + 1568] = T.max(conv2d_nchw_1[cse_var_3 + 14] + bias_1[blockIdx_x * 64 + threadIdx_x // 7 * 2 + i1_inner + 32], T.float32(0))
+ compute_1[blockIdx_x // 7 * 6272 + threadIdx_x * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i1_inner * 7 + i3_inner] + bias_1[blockIdx_x // 7 * 128 + threadIdx_x * 2 + i1_inner], T.float32(0))
@@ -786,7 +765,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.360 ms
+ Execution time of this operator: 0.342 ms
@@ -834,36 +813,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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=7)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_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_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_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)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=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=7)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -883,12 +862,12 @@ 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=112)
+ 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=64)
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=4)
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=112)
+ 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=64)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -915,399 +894,429 @@ 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__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[28];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[9216];
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[21] = 0.000000e+00f;
conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[22] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[23] = 0.000000e+00f;
conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[24] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[25] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[26] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[27] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- 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 * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 64) {
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4592) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4704) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4816)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4816) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4928) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 5040)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 161280)];
- kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5152) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5264)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5264) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5376) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5488)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5488) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5600) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5712)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5712) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5824) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5936)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5936) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 193536)];
- kernel_shared[(((int)threadIdx.x) + 6160)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6160) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6272) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6384)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6384) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6496)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6496) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 6608)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6608) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6720)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6720) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6832)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6832) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6944)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6944) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 7056)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 225792)];
- kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7280)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7392)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7504)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7504) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 7616)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7616) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7728)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7728) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7840)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7952)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7952) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 8176)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8288)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8400)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8512)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 8624)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8624) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8736)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8736) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8848)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8848) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 9072)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 290304)];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 9184)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 9184) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 112)];
- }
- __syncthreads();
- for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 64) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 128) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((((((int)threadIdx.x) + 256) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 320) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 512) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((((((int)threadIdx.x) + 640) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 704) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((((((int)threadIdx.x) + 832) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 896) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((((((int)threadIdx.x) + 1024) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1088) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((((((int)threadIdx.x) + 1216) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1280) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((((((int)threadIdx.x) + 1408) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1472) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((((((int)threadIdx.x) + 1600) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1664) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((((((int)threadIdx.x) + 1792) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1856) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((((((int)threadIdx.x) + 1984) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2048) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((((((int)threadIdx.x) + 2176) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2240) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((((((int)threadIdx.x) + 2368) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2432) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((((((int)threadIdx.x) + 2560) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2624) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((((((int)threadIdx.x) + 2752) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2816) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((((((int)threadIdx.x) + 2944) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 3008) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 1568)] = max((conv2d_nchw[(((i1_inner * 7) + i2_inner) + 14)] + bias[((((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 32)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -1368,7 +1377,7 @@ 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 13.990 seconds)
+ **Total running time of the script:** ( 6 minutes 33.263 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 6b8f1762a3..c60f815e12 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.0991 8.0963 8.1155 8.0854 0.0124
+ 8.1076 8.1102 8.1201 8.0926 0.0114
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.538 seconds)
+ **Total running time of the script:** ( 1 minutes 14.351 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 2bcb54e756..d47e3d7896 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)
- 752.8227 753.6648 754.0578 750.7456 1.4775
+ 771.7696 772.9308 774.5017 767.8764 2.8266
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 43.127 seconds)
+ **Total running time of the script:** ( 1 minutes 47.091 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 e14302e9d7..56df76e381 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
@@ -389,75 +389,26 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- for i0_outer in T.parallel(2):
+ for i0_outer_i1_outer_fused in T.parallel(32):
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(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i1_outer * 2 + nb_j_inner}), 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))
+ compute_2 = T.Buffer((2048,), data=compute_1)
+ for i_outer_inner, nb_j_inner in T.grid(8, 2):
+ for i_inner_init, j_init in T.grid(8, 16):
+ compute_2[i_outer_inner * 256 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 8, 16):
+ cse_var_1 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_outer_inner * 256 + i_inner * 32 + nb_j_inner * 16 + j
+ placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
+ placeholder_7 = T.Buffer((32768,), data=placeholder.data)
+ placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 16384 + i_outer_inner * 2048 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner, i1_inner in T.grid(64, 32):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
+ compute_3 = T.Buffer((65536,), data=compute.data)
+ placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
+ compute_3[cse_var_4] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_4], T.float32(0))
@@ -507,7 +458,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.802 ms
+ Execution time of this operator: 1.590 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 a86fcf9c39..7a2071b399 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,16 +5,16 @@
Computation times
=================
-**00:47.201** total execution time for **how_to_tune_with_autotvm** files:
+**00:35.347** 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``) | 00:47.166 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:35.312 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.022 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.004 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.004 | 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 f0dd0a21e8..7983720dfd 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, 1, 2, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2388758
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3568698
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -513,9 +513,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6798376
- No: 3 GFLOPS: 9.40/9.40 result: MeasureResult(costs=(0.024635136833333335,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.562204360961914, timestamp=1680803428.0066042) [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8009137
- No: 4 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,769270
+ No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -637,8 +636,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9133037
- No: 5 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1302615
+ No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -760,8 +759,8 @@ 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, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2321242
- No: 6 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7311343
+ No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -883,8 +882,8 @@ 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, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6808465
- No: 7 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5585613
+ No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1006,8 +1005,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9317402
- No: 8 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4568449
+ No: 7 GFLOPS: 7.98/7.98 result: MeasureResult(costs=(0.02902224725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.405341386795044, timestamp=1680811582.5334728) [('tile_f', [-1, 2, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3968262
+ No: 8 GFLOPS: 0.00/7.98 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1129,9 +1129,8 @@ 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, 2, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4065594
- No: 9 GFLOPS: 9.48/9.48 result: MeasureResult(costs=(0.02441596216666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.508664846420288, timestamp=1680803440.8370838) [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4849211
- No: 10 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8567258
+ No: 9 GFLOPS: 0.00/7.98 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
@@ -1253,8 +1252,9 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10083769
- No: 11 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6937915
+ No: 10 GFLOPS: 112.40/112.40 result: MeasureResult(costs=(0.002059589918367347,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.452477216720581, timestamp=1680811584.1773179) [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5740500
+ No: 11 GFLOPS: 0.00/112.40 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
@@ -1376,8 +1376,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2491385
- No: 12 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2563414
+ No: 12 GFLOPS: 0.00/112.40 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
@@ -1499,8 +1499,10 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5566086
- No: 13 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,958618
+ No: 13 GFLOPS: 230.73/230.73 result: MeasureResult(costs=(0.0010033478562091504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6993286609649658, timestamp=1680811587.3408077) [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4073430
+ No: 14 GFLOPS: 19.77/230.73 result: MeasureResult(costs=(0.011709251333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.626004457473755, timestamp=1680811588.2659273) [('tile_f', [-1, 32, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7755060
+ No: 15 GFLOPS: 0.00/230.73 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
@@ -1622,8 +1624,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2708616
- No: 14 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3240986
+ No: 16 GFLOPS: 0.00/230.73 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
@@ -1745,9 +1747,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7391189
- No: 15 GFLOPS: 175.28/175.28 result: MeasureResult(costs=(0.00132072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.587515115737915, timestamp=1680803445.678157) [('tile_f', [-1, 1, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8567099
- No: 16 GFLOPS: 0.00/175.28 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2001396
+ No: 17 GFLOPS: 0.00/230.73 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
@@ -1869,8 +1870,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8036476
- No: 17 GFLOPS: 0.00/175.28 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10147151
+ No: 18 GFLOPS: 0.00/230.73 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
@@ -1992,9 +1993,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7213737
- No: 18 GFLOPS: 26.18/175.28 result: MeasureResult(costs=(0.008842506333333335,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6490862369537354, timestamp=1680803447.536689) [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5488705
- No: 19 GFLOPS: 0.00/175.28 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4530870
+ No: 19 GFLOPS: 0.00/230.73 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
@@ -2116,8 +2116,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9905664
- No: 20 GFLOPS: 0.00/175.28 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7515826
+ No: 20 GFLOPS: 0.00/230.73 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
@@ -2239,7 +2239,7 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7846483
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5358497
@@ -2294,9 +2294,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8567099
+ [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4073430
Finish loading 20 records
- Time cost of this operator: 0.001716
+ Time cost of this operator: 0.001413
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 fa27cfd7d3..7a41e81a0f 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -360,10 +360,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.3 98.748 (1, 2, 10, 10, 3) 2 1 [316.3]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.95 (1, 6, 10, 10) 1 1 [3.042]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.303 (1, 1, 10, 10, 3) 1 1 [0.969]
- Total_time - 320.311 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.5 98.739 (1, 2, 10, 10, 3) 2 1 [313.5]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.958 (1, 6, 10, 10) 1 1 [3.042]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.303 (1, 1, 10, 10, 3) 1 1 [0.962]
+ Total_time - 317.504 - - - - -
@@ -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 107.2 97.628 (1, 6, 10, 10, 1) 2 1 [107.2]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.765 1.607 (1, 6, 10, 10) 1 1 [1.765]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.839 0.764 (1, 3, 10, 10, 1) 1 1 [0.839]
- Total_time - 109.804 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.8 97.996 (1, 6, 10, 10, 1) 2 1 [134.8]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.796 1.306 (1, 6, 10, 10) 1 1 [1.796]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.698 (1, 1, 10, 10, 3) 1 1 [0.96]
+ Total_time - 137.556 - - - - -
@@ -439,7 +439,7 @@ Timing the tuned program
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 22.653 seconds)
+ **Total running time of the script:** ( 1 minutes 26.673 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 8e252743ca..0b7c1bcd4a 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, 45.7MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
66%|######5 | 2.25M/3.42M [00:00<00:00, 23.6MB/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 33.6MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -324,7 +324,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 18.838 seconds)
+ **Total running time of the script:** ( 1 minutes 22.740 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 30275d75ba..2412bc039e 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -217,7 +217,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpww30hnfu/images/random'
+ '/tmp/tmp4ulcyl6c/images/random'
@@ -308,7 +308,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
+ :alt: [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -317,8 +317,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpww30hnfu/images/target contains 8144 images
- /tmp/tmpww30hnfu/images/random contains 5000 images
+ /tmp/tmp4ulcyl6c/images/target contains 8144 images
+ /tmp/tmp4ulcyl6c/images/random contains 5000 images
@@ -493,13 +493,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 39s - loss: 0.2041 - accuracy: 0.9268 - val_loss: 0.1426 - val_accuracy: 0.9505 - 39s/epoch - 120ms/step
+ 328/328 - 41s - loss: 0.2110 - accuracy: 0.9261 - val_loss: 0.1376 - val_accuracy: 0.9566 - 41s/epoch - 126ms/step
Epoch 2/3
- 328/328 - 35s - loss: 0.1003 - accuracy: 0.9645 - val_loss: 0.1111 - val_accuracy: 0.9619 - 35s/epoch - 105ms/step
+ 328/328 - 35s - loss: 0.0943 - accuracy: 0.9641 - val_loss: 0.1931 - val_accuracy: 0.9377 - 35s/epoch - 107ms/step
Epoch 3/3
- 328/328 - 34s - loss: 0.0673 - accuracy: 0.9734 - val_loss: 0.1161 - val_accuracy: 0.9641 - 34s/epoch - 105ms/step
+ 328/328 - 35s - loss: 0.0695 - accuracy: 0.9748 - val_loss: 0.1634 - val_accuracy: 0.9434 - 35s/epoch - 106ms/step
- <keras.callbacks.History object at 0x7f09c81fc990>
+ <keras.callbacks.History object at 0x7fc43f735f90>
@@ -860,7 +860,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 31.196 seconds)
+ **Total running time of the script:** ( 4 minutes 36.848 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 341b72118b..b7dea76acd 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,20 +5,20 @@
Computation times
=================
-**07:38.761** total execution time for **how_to_work_with_microtvm** files:
+**07:53.941** total execution time for **how_to_work_with_microtvm** files:
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:31.196 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:36.848 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:22.653 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 01:26.673 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:18.838 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:22.740 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:10.444 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:11.015 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:08.081 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_custom_ide.py` (``micro_custom_ide.py``) | 00:08.794 | 0.0 MB |
+-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.548 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:07.870 | 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 170bd5ea9a..33eed6cf0e 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:36.757** total execution time for **how_to_work_with_relay** files:
+**00:39.468** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:32.268 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:34.455 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:02.880 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:03.080 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.603 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.926 | 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 |
+| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 2f9c5e9f3e..81156a19e4 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -278,7 +278,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f074add9d40>
+ <function my_cuda_math_rule at 0x7fc08d8645f0>
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 d3ba5bb89d..8fb7f49acd 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:08.294** total execution time for **how_to_work_with_schedules** files:
+**00:09.340** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:05.474 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:06.372 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.294 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.366 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.631 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.664 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.614 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.640 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.132 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.139 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.065 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.066 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.055 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.061 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.030 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.033 | 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 5f2d687c01..b7edbf6bcb 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
=================
-**00:31.580** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:32.985** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:31.573 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:32.978 | 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 11ee5b14e0..b537f35427 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 33.64s!
+ resnet18_v1 inference graph built in 35.72s!
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 6a20a2e266..f22e3dbb4d 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 22.85s!
+ yolov3-tiny inference graph built in 24.12s!
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 d1d33b61ab..1318a9e3bf 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
=================
-**01:40.500** total execution time for **topic_vta_tutorials_frontend** files:
+**01:44.421** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:50.554 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:52.797 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.947 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:51.623 | 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 3414211c70..439722a770 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
=================
-**00:03.177** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.264** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.697 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.760 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.481 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.503 | 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 1798f25620..06defaf613 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
=================
-**00:00.830** total execution time for **topic_vta_tutorials** files:
+**00:00.860** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.429 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.444 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.401 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.416 | 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 e3de40a607..ef6c34c8a9 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,6 +207,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ *E
+
+
@@ -318,7 +325,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.727 ms
+ Execution time of this operator: 98.647 ms
@@ -434,7 +441,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 36.586 seconds)
+ **Total running time of the script:** ( 1 minutes 36.346 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 480df20874..79e9c8b52f 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: 10.24/10.24 result: MeasureResult(costs=(0.0262073602,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7390856742858887, timestamp=1680801739.0798178) [('tile_y', [-1, 16]), ('tile_x', [-1, 32])],None,54
- No: 2 GFLOPS: 0.80/10.24 result: MeasureResult(costs=(0.3339578552,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.58829140663147, timestamp=1680801744.6909096) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 3 GFLOPS: 8.25/10.24 result: MeasureResult(costs=(0.0325340484,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.780775785446167, timestamp=1680801746.7403245) [('tile_y', [-1, 2]), ('tile_x', [-1, 64])],None,61
- No: 4 GFLOPS: 10.64/10.64 result: MeasureResult(costs=(0.0252402758,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6762723922729492, timestamp=1680801748.6599727) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
- No: 5 GFLOPS: 3.08/10.64 result: MeasureResult(costs=(0.0870337288,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.635138988494873, timestamp=1680801750.5050821) [('tile_y', [-1, 128]), ('tile_x', [-1, 8])],None,37
- No: 6 GFLOPS: 12.78/12.78 result: MeasureResult(costs=(0.021003902999999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.678776741027832, timestamp=1680801751.1062706) [('tile_y', [-1, 256]), ('tile_x', [-1, 128])],None,78
- No: 7 GFLOPS: 11.54/12.78 result: MeasureResult(costs=(0.023262110199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6071891784667969, timestamp=1680801753.0000832) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
- No: 8 GFLOPS: 3.15/12.78 result: MeasureResult(costs=(0.08534624119999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6156713962554932, timestamp=1680801754.6239653) [('tile_y', [-1, 512]), ('tile_x', [-1, 16])],None,49
- No: 9 GFLOPS: 9.71/12.78 result: MeasureResult(costs=(0.0276530636,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.650679349899292, timestamp=1680801755.3954105) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
- No: 10 GFLOPS: 0.90/12.78 result: MeasureResult(costs=(0.299922375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.005521774291992, timestamp=1680801760.4501207) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+ No: 1 GFLOPS: 1.61/1.61 result: MeasureResult(costs=(0.16717953079999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.9362173080444336, timestamp=1680809815.8257272) [('tile_y', [-1, 64]), ('tile_x', [-1, 4])],None,26
+ No: 2 GFLOPS: 0.85/1.61 result: MeasureResult(costs=(0.3158561498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.311703681945801, timestamp=1680809821.1491442) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
+ No: 3 GFLOPS: 8.62/8.62 result: MeasureResult(costs=(0.031141408199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9014453887939453, timestamp=1680809823.2560456) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
+ No: 4 GFLOPS: 0.50/8.62 result: MeasureResult(costs=(0.5331877478,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.767101764678955, timestamp=1680809832.0531905) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
+ No: 5 GFLOPS: 10.53/10.53 result: MeasureResult(costs=(0.025485306000000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6884784698486328, timestamp=1680809832.8680763) [('tile_y', [-1, 32]), ('tile_x', [-1, 256])],None,85
+ No: 6 GFLOPS: 2.31/10.53 result: MeasureResult(costs=(0.1161488554,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1144587993621826, timestamp=1680809836.3425992) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 7 GFLOPS: 1.53/10.53 result: MeasureResult(costs=(0.1750596042,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.05776047706604, timestamp=1680809840.7654943) [('tile_y', [-1, 16]), ('tile_x', [-1, 1])],None,4
+ No: 8 GFLOPS: 9.89/10.53 result: MeasureResult(costs=(0.027136655200000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7110087871551514, timestamp=1680809841.4634233) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 8.69/10.53 result: MeasureResult(costs=(0.030891525200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7121789455413818, timestamp=1680809842.2998433) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
+ No: 10 GFLOPS: 2.87/10.53 result: MeasureResult(costs=(0.0934299298,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7176766395568848, timestamp=1680809844.0582802) [('tile_y', [-1, 1]), ('tile_x', [-1, 16])],None,40
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 4531ca451e..6fbd52bcd4 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': 509.35657655999756, 'median': 508.95062829999347, 'std': 1.4660641184821586}
+ {'mean': 522.765000579999, 'median': 522.4877006999975, 'std': 2.8382338743111264}
@@ -545,31 +545,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 5.27/ 17.37 GFLOPS | Progress: (4/20) | 11.68 s
[Task 1/25] Current/Best: 6.65/ 23.12 GFLOPS | Progress: (8/20) | 15.45 s
[Task 1/25] Current/Best: 22.13/ 23.12 GFLOPS | Progress: (12/20) | 17.52 s
[Task 1/25] Current/Best: 13.52/ 23.12 GFLOPS | Progress: (16/20) | 20.74 s
[Task 1/25] Current/Best: 13.55/ 23.12 GFLOPS | Progress: (20/20) | 23.22 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 10.16/ 12.33 GFLOPS | Progress: (4/20) | 6.04 s
[Task 2/25] Current/Best: 3.47/ 12.33 GFLOPS | Progress: (8/20) | 8.13 s
[Task 2/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (12/20) | 10.63 s
[Task 2/25] Current/Best: 8.96/ 19.99 GFLOPS | Progress: (16/20) | 12.24 s
[Task 2/25] Current/Best: 6.66/ 19.99 GFLOPS | Progress: (20/20) | 14.12 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 6.04/ 14.78 GFLOPS | Progress: (4/20) | 6.11 s
[Task 3/25] Current/Best: 17.23/ 17.23 GFLOPS | Progress: (8/20) | 8.65 s
[Task 3/25] Current/Best: 6.97/ 17.23 GFLOPS | Progress: (12/20) | 11.05 s
[Task 3/25] Current/Best: 1.63/ 17.23 GFLOPS | Progress: (16/20) | 14.69 s
[Task 3/25] Current/Best: 17.20/ 22.00 GFLOPS | Progress: (20/20) | 16.71 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 3.33/ 21.51 GFLOPS | Progress: (4/20) | 4.98 s
[Task 4/25] Current/Best: 12.50/ 21.51 GFLOPS | Progress: (8/20) | 7.51 s
[Task 4/25] Current/Best: 14.53/ 21.51 GFLOPS | Progress: (12/20) | 10.45 s
[Task 4/25] Current/Best: 6.40/ 21.51 GFLOPS | Progress: (16/20) | 12.93 s
[Task 4/25] Current/Best: 13.22/ 21.51 GFLOPS | Progress: (20/20) | 15.61 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 15.31/ 15.31 GFLOPS | Progress: (4/20) | 5.13 s
[Task 5/25] Current/Best: 18.04/ 18.39 GFLOPS | Progress: (8/20) | 6.82 s
[Task 5/25] Current/Best: 10.60/ 18.39 GFLOPS | Progress: (12/20) | 9.05 s
[Task 5/25] Current/Best: 14.22/ 19.55 GFLOPS | Progress: (16/20) | 10.95 s
[Task 5/25] Current/Best: 10.80/ 19.55 GFLOPS | Progress: (20/20) | 13.15 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 18.53/ 18.53 GFLOPS | Progress: (4/20) | 6.24 s
[Task 6/25] Current/Best: 17.90/ 18.53 GFLOPS | Progress: (8/20) | 8.98 s
[Task 6/25] Current/Best: 13.75/ 18.53 GFLOPS | Progress: (12/20) | 12.95 s
[Task 6/25] Current/Best: 3.77/ 18.53 GFLOPS | Progress: (16/20) | 15.52 s
[Task 6/25] Current/Best: 15.09/ 19.21 GFLOPS | Progress: (20/20) | 17.55 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.65/ 11.50 GFLOPS | Progress: (4/20) | 7.03 s
[Task 7/25] Current/Best: 8.08/ 16.64 GFLOPS | Progress: (8/20) | 10.17 s
[Task 7/25] Current/Best: 7.97/ 21.64 GFLOPS | Progress: (12/20) | 12.34 s
[Task 7/25] Current/Best: 21.53/ 21.64 GFLOPS | Progress: (16/20) | 14.21 s
[Task 7/25] Current/Best: 6.88/ 21.64 GFLOPS | Progress: (20/20) | 16.60 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 5.38/ 13.96 GFLOPS | Progress: (4/20) | 5.31 s
[Task 8/25] Current/Best: 4.62/ 13.96 GFLOPS | Progress: (8/20) | 8.19 s
[Task 8/25] Current/Best: 11.05/ 13.96 GFLOPS | Progress: (12/20) | 15.22 s
[Task 8/25] Current/Best: 20.32/ 20.32 GFLOPS | Progress: (16/20) | 17.35 s
[Task 8/25] Current/Best: 2.71/ 20.32 GFLOPS | Progress: (20/20) | 20.40 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 12.35/ 16.93 GFLOPS | Progress: (4/20) | 8.59 s
[Task 9/25] Current/Best: 7.27/ 16.93 GFLOPS | Progress: (8/20) | 19.85 s
[Task 9/25] Current/Best: 3.23/ 16.93 GFLOPS | Progress: (12/20) | 28.24 s
[Task 9/25] Current/Best: 11.63/ 16.93 GFLOPS | Progress: (16/20) | 31.10 s
[Task 9/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (20/20) | 38.74 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 5.87/ 16.24 GFLOPS | Progress: (4/20) | 4.81 s Done.
-
[Task 10/25] Current/Best: 6.46/ 16.24 GFLOPS | Progress: (8/20) | 6.94 s
[Task 10/25] Current/Best: 13.21/ 19.02 GFLOPS | Progress: (12/20) | 8.50 s
[Task 10/25] Current/Best: 15.90/ 19.02 GFLOPS | Progress: (16/20) | 11.18 s
[Task 10/25] Current/Best: 5.31/ 19.02 GFLOPS | Progress: (20/20) | 13.32 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 14.41/ 21.05 GFLOPS | Progress: (4/20) | 5.06 s
[Task 11/25] Current/Best: 17.33/ 21.05 GFLOPS | Progress: (8/20) | 7.56 s
[Task 11/25] Current/Best: 17.53/ 21.09 GFLOPS | Progress: (12/20) | 9.72 s
[Task 11/25] Current/Best: 5.96/ 21.09 GFLOPS | Progress: (16/20) | 12.22 s
[Task 11/25] Current/Best: 19.28/ 21.09 GFLOPS | Progress: (20/20) | 15.00 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.99/ 13.99 GFLOPS | Progress: (4/20) | 7.20 s
[Task 12/25] Current/Best: 14.06/ 14.44 GFLOPS | Progress: (8/20) | 10.18 s
[Task 12/25] Current/Best: 15.64/ 18.24 GFLOPS | Progress: (12/20) | 12.79 s
[Task 12/25] Current/Best: 13.52/ 18.24 GFLOPS | Progress: (16/20) | 16.00 s
[Task 12/25] Current/Best: 11.71/ 18.24 GFLOPS | Progress: (20/20) | 22.13 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 5.93/ 17.31 GFLOPS | Progress: (4/20) | 5.93 s
[Task 13/25] Current/Best: 15.12/ 17.31 GFLOPS | Progress: (8/20) | 8.62 s
[Task 13/25] Current/Best: 8.83/ 17.31 GFLOPS | Progress: (12/20) | 12.57 s
[Task 13/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (16/20) | 15.71 s
[Task 13/25] Current/Best: 6.19/ 18.79 GFLOPS | Progress: (20/20) | 19.17 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 2.76/ 12.38 GFLOPS | Progress: (4/20) | 6.13 s
[Task 14/25] Current/Best: 6.17/ 14.38 GFLOPS | Progress: (8/20) | 9.05 s
[Task 14/25] Current/Best: 18.19/ 18.37 GFLOPS | Progress: (12/20) | 11.41 s
[Task 14/25] Current/Best: 18.14/ 18.37 GFLOPS | Progress: (16/20) | 13.88 s
[Task 14/25] Current/Best: 13.42/ 18.37 GFLOPS | Progress: (20/20) | 17.64 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 22.99/ 22.99 GFLOPS | Progress: (4/20) | 4.67 s
[Task 15/25] Current/Best: 14.24/ 22.99 GFLOPS | Progress: (8/20) | 7.60 s
[Task 15/25] Current/Best: 14.21/ 22.99 GFLOPS | Progress: (12/20) | 9.68 s
[Task 15/25] Current/Best: 21.21/ 22.99 GFLOPS | Progress: (16/20) | 12.47 s
[Task 15/25] Current/Best: 6.16/ 22.99 GFLOPS | Progress: (20/20) | 14.71 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 3.08/ 18.21 GFLOPS | Progress: (4/20) | 6.16 s
[Task 16/25] Current/Best: 18.52/ 18.81 GFLOPS | Progress: (8/20) | 9.13 s
[Task 16/25] Current/Best: 9.45/ 18.81 GFLOPS | Progress: (12/20) | 11.43 s
[Task 16/25] Current/Best: 18.46/ 18.81 GFLOPS | Progress: (16/20) | 13.13 s
[Task 16/25] Current/Best: 15.01/ 18.81 GFLOPS | Progress: (20/20)
| 15.09 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.41/ 22.72 GFLOPS | Progress: (4/20) | 6.10 s
[Task 17/25] Current/Best: 9.17/ 22.72 GFLOPS | Progress: (8/20) | 9.47 s
[Task 17/25] Current/Best: 11.75/ 22.72 GFLOPS | Progress: (12/20) | 11.98 s
[Task 17/25] Current/Best: 5.08/ 22.72 GFLOPS | Progress: (16/20) | 15.52 s
[Task 17/25] Current/Best: 3.09/ 22.72 GFLOPS | Progress: (20/20) | 18.25 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 6.09/ 9.08 GFLOPS | Progress: (4/20) | 7.35 s
[Task 18/25] Current/Best: 5.92/ 15.23 GFLOPS | Progress: (8/20) | 11.27 s
[Task 18/25] Current/Best: 8.90/ 17.74 GFLOPS | Progress: (12/20) | 15.83 s
[Task 18/25] Current/Best: 16.17/ 19.05 GFLOPS | Progress: (16/20) | 22.00 s
[Task 18/25] Current/Best: 10.06/ 19.05 GFLOPS | Progress: (20/20) | 29.26 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 18.09/ 18.09 GFLOPS | Progress: (4/20) | 7.06 s
[Task 19/25] Current/Best: 10.46/ 18.09 GFLOPS | Progress: (8/20) | 11.49 s
[Task 19/25] Current/Best: 6.43/ 19.60 GFLOPS | Progress: (12/20) | 14.72 s
[Task 19/25] Current/Best: 18.74/ 20.40 GFLOPS | Progress: (16/20) | 18.34 s
[Task 19/25] Current/Best: 18.20/ 20.40 GFLOPS | Progress: (20/20) | 21.89 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 10.44/ 14.03 GFLOPS | Progress: (4/20) | 5.12 s Done.
-
[Task 20/25] Current/Best: 17.33/ 18.43 GFLOPS | Progress: (8/20) | 9.54 s
[Task 20/25] Current/Best: 17.12/ 19.60 GFLOPS | Progress: (12/20) | 11.42 s
[Task 20/25] Current/Best: 14.02/ 19.60 GFLOPS | Progress: (16/20) | 15.28 s
[Task 20/25] Current/Best: 6.70/ 19.60 GFLOPS | Progress: (20/20) | 19.18 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 19.02/ 19.02 GFLOPS | Progress: (4/20) | 4.42 s
[Task 21/25] Current/Best: 15.58/ 19.02 GFLOPS | Progress: (8/20) | 7.12 s
[Task 21/25] Current/Best: 18.28/ 19.02 GFLOPS | Progress: (12/20) | 10.12 s
[Task 21/25] Current/Best: 7.06/ 19.02 GFLOPS | Progress: (16/20) | 12.31 s
[Task 21/25] Current/Best: 12.99/ 19.02 GFLOPS | Progress: (20/20) | 13.80 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 11.56/ 17.97 GFLOPS | Progress: (4/2
0) | 6.68 s
[Task 22/25] Current/Best: 16.72/ 17.97 GFLOPS | Progress: (8/20) | 8.66 s
[Task 22/25] Current/Best: 9.94/ 17.97 GFLOPS | Progress: (12/20) | 11.80 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 12.32/ 18.77 GFLOPS | Progress: (4/20) | 10.12 s
[Task 1/25] Current/Best: 22.59/ 22.59 GFLOPS | Progress: (8/20) | 15.34 s
[Task 1/25] Current/Best: 3.20/ 22.59 GFLOPS | Progress: (12/20) | 18.18 s
[Task 1/25] Current/Best: 6.54/ 22.59 GFLOPS | Progress: (16/20) | 21.00 s
[Task 1/25] Current/Best: 12.87/ 23.15 GFLOPS | Progress: (20/20) | 23.07 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 4.28/ 12.67 GFLOPS | Progress: (4/20) | 4.74 s
[Task 2/25] Current/Best: 12.23/ 16.38 GFLOPS | Progress: (8/20) | 6.49 s
[Task 2/25] Current/Best: 7.50/ 20.78 GFLOPS | Progress: (12/20) | 7.89 s
[Task 2/25] Current/Best: 18.98/ 20.78 GFLOPS | Progress: (16/20) | 10.20 s
[Task 2/25] Current/Best: 14.14/ 20.78 GFLOPS | Progress: (20/20) | 11.81 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 14.52/ 22.16 GFLOPS | Progress: (4/20) | 5.34 s
[Task 3/25] Current/Best: 17.58/ 22.16 GFLOPS | Progress: (8/20) | 8.24 s
[Task 3/25] Current/Best: 8.38/ 22.16 GFLOPS | Progress: (12/20) | 11.16 s
[Task 3/25] Current/Best: 11.34/ 22.16 GFLOPS | Progress: (16/20) | 13.93 s
[Task 3/25] Current/Best: 22.63/ 22.63 GFLOPS | Progress: (20/20) | 16.32 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.53/ 12.67 GFLOPS | Progress: (4/20) | 9.02 s
[Task 4/25] Current/Best: 17.09/ 21.38 GFLOPS | Progress: (8/20) | 10.63 s
[Task 4/25] Current/Best: 16.59/ 21.38 GFLOPS | Progress: (12/20) | 12.62 s
[Task 4/25] Current/Best: 14.26/ 21.38 GFLOPS | Progress: (16/20) | 14.91 s
[Task 4/25] Current/Best: 10.36/ 21.38 GFLOPS | Progress: (20/20) | 20.73 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 14.13/ 14.13 GFLOPS | Progress: (4/20) | 4.93 s
[Task 5/25] Current/Best: 12.06/ 20.13 GFLOPS | Progress: (8/20) | 7.09 s
[Task 5/25] Current/Best: 11.18/ 20.13 GFLOPS | Progress: (12/20) | 9.17 s
[Task 5/25] Current/Best: 10.05/ 20.93 GFLOPS | Progress: (16/20) | 11.74 s
[Task 5/25] Current/Best: 10.38/ 20.93 GFLOPS | Progress: (20/20) | 14.30 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 13.58/ 19.28 GFLOPS | Progress: (4/20) | 6.49 s
[Task 6/25] Current/Best: 10.16/ 19.28 GFLOPS | Progress: (8/20) | 14.51 s
[Task 6/25] Current/Best: 5.70/ 19.28 GFLOPS | Progress: (12/20) | 17.79 s
[Task 6/25] Current/Best: 4.41/ 19.28 GFLOPS | Progress: (16/20) | 20.96 s
[Task 6/25] Current/Best: 20.64/ 20.64 GFLOPS | Progress: (20/20) | 24.62 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 17.13/ 17.13 GFLOPS | Progress: (4/20) | 5.85 s
[Task 7/25] Current/Best: 7.72/ 18.07 GFLOPS | Progress: (8/20) | 8.52 s
[Task 7/25] Current/Best: 15.69/ 18.07 GFLOPS | Progress: (12/20) | 11.30 s
[Task 7/25] Current/Best: 15.33/ 20.26 GFLOPS | Progress: (16/20) | 13.46 s
[Task 7/25] Current/Best: 15.28/ 20.26 GFLOPS | Progress: (20/20) | 15.88 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 4.72/ 16.51 GFLOPS | Progress: (4/20) | 11.20 s
[Task 8/25] Current/Best: 15.70/ 16.51 GFLOPS | Progress: (8/20) | 14.15 s
[Task 8/25] Current/Best: 19.39/ 19.39 GFLOPS | Progress: (12/20) | 17.10 s
[Task 8/25] Current/Best: 9.34/ 19.39 GFLOPS | Progress: (16/20) | 20.68 s
[Task 8/25] Current/Best: 5.76/ 19.39 GFLOPS | Progress: (20/20) | 23.59 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 11.29/ 11.29 GFLOPS | Progress: (4/20) | 6.77 s
[Task 9/25] Current/Best: 15.17/ 15.17 GFLOPS | Progress: (8/20) | 10.63 s
[Task 9/25] Current/Best: 15.53/ 15.53 GFLOPS | Progress: (12/20) | 12.46 s
[Task 9/25] Current/Best: 17.79/ 18.07 GFLOPS | Progress: (16/20) | 19.80 s
[Task 9/25] Current/Best: 18.40/ 18.43 GFLOPS | Progress: (20/20) | 23.60 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 7.69/ 10.22 GFLOPS | Progress: (4/20) | 6.73 s
[Task 10/25] Current/Best: 9.65/ 17.89 GFLOPS | Progress: (8/20) | 10.91 s
[Task 10/25] Current/Best: 4.16/ 17.89 GFLOPS | Progress: (12/20) | 12.97 s
[Task 10/25] Current/Best: 15.50/ 17.90 GFLOPS | Progress: (16/20) | 17.08 s
[Task 10/25] Current/Best: 11.28/ 17.90 GFLOPS | Progress: (20/20) | 19.15 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 7.78/ 11.61 GFLOPS | Progress: (4/20) | 6.77 s
[Task 11/25] Current/Best: 15.86/ 21.68 GFLOPS | Progress: (8/20) | 10.42 s
[Task 11/25] Current/Best: 3.10/ 21.68 GFLOPS | Progress: (12/20) | 13.83 s
[Task 11/25] Current/Best: 14.57/ 21.68 GFLOPS | Progress: (16/20) | 16.33 s
[Task 11/25] Current/Best: 18.70/ 21.68 GFLOPS | Progress: (20/20) | 18.97 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 13.27/ 14.00 GFLOPS | Progress: (4/20) | 5.71 s
[Task 12/25] Current/Best: 3.05/ 15.60 GFLOPS | Progress: (8/20) | 15.32 s
[Task 12/25] Current/Best: 4.28/ 18.48 GFLOPS | Progress: (12/20) | 22.58 s
[Task 12/25] Current/Best: 4.26/ 18.48 GFLOPS | Progress: (16/20) | 25.30 s
[Task 12/25] Current/Best: 16.21/ 20.18 GFLOPS | Progress: (20/20) | 27.47 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 19.72/ 20.06 GFLOPS | Progress: (4/20) | 6.10 s
[Task 13/25] Current/Best: 6.56/ 21.85 GFLOPS | Progress: (8/20) | 9.98 s
[Task 13/25] Current/Best: 18.52/ 21.85 GFLOPS | Progress: (12/20) | 13.61 s
[Task 13/25] Current/Best: 18.52/ 21.85 GFLOPS | Progress: (16/20) | 16.82 s
[Task 13/25] Current/Best: 6.93/ 21.85 GFLOPS | Progress: (20/20) | 20.25 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 15.67/ 15.67 GFLOPS | Progress: (4/20) | 5.37 s
[Task 14/25] Current/Best: 10.42/ 18.18 GFLOPS | Progress: (8/20) | 7.88 s
[Task 14/25] Current/Best: 8.82/ 18.18 GFLOPS | Progress: (12/20) | 11.00 s
[Task 14/25] Current/Best: 16.11/ 18.18 GFLOPS | Progress: (16/20) | 13.99 s
[Task 14/25] Current/Best: 11.36/ 18.18 GFLOPS | Progress: (20/20) | 17.19 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 20.82/ 20.82 GFLOPS | Progress: (4/20) | 5.75 s
[Task 15/25] Current/Best: 15.20/ 20.82 GFLOPS | Progress: (8/20) | 8.53 s
[Task 15/25] Current/Best: 15.26/ 20.82 GFLOPS | Progress: (12/20) | 11.88 s
[Task 15/25] Current/Best: 14.12/ 20.82 GFLOPS | Progress: (16/20) | 14.97 s
[Task 15/25] Current/Best: 16.51/ 20.82 GFLOPS | Progress: (20/20
) | 16.94 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 5.64/ 18.91 GFLOPS | Progress: (4/20) | 4.77 s
[Task 16/25] Current/Best: 15.48/ 18.91 GFLOPS | Progress: (8/20) | 7.03 s
[Task 16/25] Current/Best: 12.06/ 19.22 GFLOPS | Progress: (12/20) | 8.76 s
[Task 16/25] Current/Best: 1.56/ 19.22 GFLOPS | Progress: (16/20) | 11.34 s
[Task 16/25] Current/Best: 18.46/ 19.22 GFLOPS | Progress: (20/20) | 14.30 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (4/20) | 5.63 s
[Task 17/25] Current/Best: 1.56/ 20.61 GFLOPS | Progress: (8/20) | 10.40 s Done.
+
[Task 17/25] Current/Best: 12.03/ 22.55 GFLOPS | Progress: (12/20) | 12.79 s
[Task 17/25] Current/Best: 12.20/ 22.55 GFLOPS | Progress: (16/20) | 15.02 s
[Task 17/25] Current/Best: 12.15/ 22.55 GFLOPS | Progress: (20/20) | 18.12 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.31/ 16.00 GFLOPS | Progress: (4/20) | 5.87 s
[Task 18/25] Current/Best: 15.01/ 16.00 GFLOPS | Progress: (8/20) | 10.24 s
[Task 18/25] Current/Best: 18.79/ 18.79 GFLOPS | Progress: (12/20) | 12.11 s
[Task 18/25] Current/Best: 12.84/ 18.79 GFLOPS | Progress: (16/20) | 14.11 s
[Task 18/25] Current/Best: 15.94/ 18.79 GFLOPS | Progress: (20/20) | 17.24 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 11.89/ 17.82 GFLOPS | Progress: (4/20) | 6.00 s
[Task 19/25] Current/Best: 5.04/ 17.93 GFLOPS | Progress: (8/20) | 11.62 s
[Task 19/25] Current/Best: 6.13/ 17.93 GFLOPS | Progress: (12/20) | 15.23 s
[Task 19/25] Current/Best: 10.44/ 22.26 GFLOPS | Progress: (16/20) | 20.93 s
[Task 19/25] Current/Best: 12.05/ 22.26 GFLOPS | Progress: (20/20) | 25.37 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.91/ 11.07 GFLOPS | Progress: (4/20) | 6.39 s
[Task 20/25] Current/Best: 18.36/ 19.12 GFLOPS | Progress: (8/20) | 9.55 s
[Task 20/25] Current/Best: 5.16/ 19.12 GFLOPS | Progress: (12/20) | 13.03 s
[Task 20/25] Current/Best: 12.36/ 19.12 GFLOPS | Progress: (16/20) | 16.35 s
[Task 20/25] Current/Best: 7.63/ 19.12 GFLOPS | Progress: (20/20) | 20.18 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 9.58/ 9.58 GFLOPS | Progress: (4/20) | 5.88 s Done.
+
[Task 21/25] Current/Best: 5.27/ 16.06 GFLOPS | Progress: (8/20) | 9.65 s
[Task 21/25] Current/Best: 11.10/ 18.50 GFLOPS | Progress: (12/20) | 11.54 s
[Task 21/25] Current/Best: 7.52/ 18.50 GFLOPS | Progress: (16/20) | 14.97 s
[Task 21/25] Current/Best: 4.39/ 22.39 GFLOPS | Progress: (20/20) | 17.31 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 11.66/ 16.07 GFLOPS | Progress: (4/20) | 6.31 s
[Task 22/25] Current/Best: 17.84/ 17.84 GFLOPS | Progress: (8/20) | 8.25 s
[Task 22/25] Current/Best: 4.68/ 17.84 GFLOPS | Progress: (12/20) | 10.76 s
[Task 22/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (16/20) | 16.40 s
[Task 22/25] Current/Best: 15.73/ 19.44 GFLOPS | Progress: (20/20) | 18.41 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 10.89/ 18.42 GFLOPS | Progress: (4/20) | 6.01 s
[Task 23/25] Current/Best: 4.14/ 18.42 GFLOPS | Progress: (8/20) | 9.51 s
[Task 23/25] Current/Best: 11.85/ 22.78 GFLOPS | Progress: (12/20) | 12.00 s
[Task 23/25] Current/Best: 3.07/ 22.78 GFLOPS | Progress: (16/20) | 14.98 s
[Task 23/25] Current/Best: 2.53/ 22.78 GFLOPS | Progress: (20/20) | 18.12 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 9.22/ 9.22 GFLOPS | Progress: (4/20) | 5.05 s
[Task 24/25] Current/Best: 5.42/ 9.82 GFLOPS | Progress: (8/20) | 16.04 s
[Task 24/25] Current/Best: 4.04/ 9.82 GFLOPS | Progress: (12/20) | 28.14 s
[Task 24/25] Current/Best: 5.02/ 9.82 GFLOPS | Progress: (16/20) | 32.38 s
[Task 24/25] Current/Best: 2.14/ 9.82 GFLOPS | Progress: (20/20) | 43.38 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 22/25] Current/Best: 16.73/ 18.67 GFLOPS | Progress: (16/20) | 13.55 s
[Task 22/25] Current/Best: 12.92/ 18.67 GFLOPS | Progress: (20/20) | 16.65 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 5.59/ 12.94 GFLOPS | Progress: (4/20) | 9.11 s
[Task 23/25] Current/Best: 6.13/ 12.94 GFLOPS | Progress: (8/20) | 12.39 s
[Task 23/25] Current/Best: 10.34/ 18.68 GFLOPS | Progress: (12/20) | 16.99 s
[Task 23/25] Current/Best: 3.08/ 18.68 GFLOPS | Progress: (16/20) | 20.32 s
[Task 23/25] Current/Best: 11.85/ 18.68 GFLOPS | Progress: (20/20) | 23.34 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.32/ 10.14 GFLOPS | Progress: (4/20) | 7.83 s
[Task 24/25] Current/Best: 1.62/ 10.14 GFLOPS | Progress: (8/20) | 18.51 s
[Task 24/25] Current/Best: 1.89/ 10.14 GFLOPS | Progress: (12/20) | 31.50 s
[Task 24/25] Current/Best: 7.78/ 10.14 GFLOPS | Progress: (16/20) | 34.11 s
[Task 24/25] Current/Best: 4.08/ 10.14 GFLOPS | Progress: (20/20) | 45.10 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 5.59/ 8.90 GFLOPS | Progress: (4/20) | 5.67 s Done.
-
[Task 25/25] Current/Best: 8.24/ 8.95 GFLOPS | Progress: (8/20) | 16.61 s
[Task 25/25] Current/Best: 2.72/ 8.95 GFLOPS | Progress: (12/20) | 23.33 s
[Task 25/25] Current/Best: 8.09/ 9.65 GFLOPS | Progress: (16/20) | 34.26 s
[Task 25/25] Current/Best: 9.21/ 9.65 GFLOPS | Progress: (20/20) | 45.21 s
+ Done.
+
[Task 25/25] Current/Best: 5.40/ 8.06 GFLOPS | Progress: (4/20) | 8.97 s
[Task 25/25] Current/Best: 7.73/ 8.06 GFLOPS | Progress: (8/20) | 10.68 s
[Task 25/25] Current/Best: 3.56/ 8.06 GFLOPS | Progress: (12/20) | 20.22 s
[Task 25/25] Current/Best: 3.69/ 8.16 GFLOPS | Progress: (16/20) | 22.85 s
[Task 25/25] Current/Best: 6.88/ 8.16 GFLOPS | Progress: (20/20) | 33.83 s
@@ -723,8 +723,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 421.38074306000135, 'median': 420.7405058499944, 'std': 4.408706496771825}
- unoptimized: {'mean': 509.35657655999756, 'median': 508.95062829999347, 'std': 1.4660641184821586}
+ optimized: {'mean': 412.4766693599963, 'median': 412.66507015000116, 'std': 0.9249494224165179}
+ unoptimized: {'mean': 522.765000579999, 'median': 522.4877006999975, 'std': 2.8382338743111264}
@@ -747,7 +747,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 38.397 seconds)
+ **Total running time of the script:** ( 12 minutes 40.497 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 fa6269ec29..58d118516e 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
- 1.353e-07 secs/op
+ 1.626e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 96b1d85ba9..3b7da96803 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -270,7 +270,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x247bee40)), stage(b, placeholder(b, 0x103486b0)), 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, 0x127a66d0)), stage(b, placeholder(b, 0x133aa8e0)), 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 92a473d91c..cb6ff770ba 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**16:21.787** total execution time for **tutorial** files:
+**16:39.798** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:38.397 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:40.497 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:36.586 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:36.346 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.414 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:03.163 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:37.171 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:38.812 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:28.683 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:38.252 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.519 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.632 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.845 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.894 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.171 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.202 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 5a679f7320..85d0c33ddf 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -285,7 +285,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000008
@@ -389,7 +389,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000010
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.28836999971827e-06 1.0
- naive 7.8446e-06 0.9464587126620367
- parallel 6.965399999999999e-06 0.8403823671284898
- vector 2.4687899999999998e-05 2.978619439146559
+ numpy 6.88196000055541e-06 1.0
+ naive 7.964999999999999e-06 1.1573737713321761
+ parallel 9.721900000000001e-06 1.4126644152560308
+ vector 2.4681799999999998e-05 3.586449208947458
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018819
+ Numpy running time: 0.020344
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.200368
+ none: 3.462787
@@ -1080,7 +1080,7 @@ schedule.
.. code-block:: none
- blocking: 0.299997
+ blocking: 0.335493
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.338025
+ vectorization: 0.356492
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1230,7 +1230,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.118160
+ loop permutation: 0.139470
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1321,7 +1321,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109923
+ array packing: 0.108075
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1404,7 +1404,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111022
+ block caching: 0.111215
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1478,7 +1478,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146543
+ parallelization: 0.147326
# from tvm.script import ir as I
# from tvm.script import tir as T
@@ -1548,13 +1548,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2003681018999997 1.0
- blocking 0.29999666269999997 0.09373817421873987
- vectorization 0.3380245563 0.10562052412012263
- loop permutation 0.1181604115 0.03692088151667627
- array packing 0.10992314630000002 0.034347032216306826
- block caching 0.1110223328 0.034690488489148505
- parallelization 0.14654285420000002 0.04578937470130396
+ none 3.4627870992999994 1.0
+ blocking 0.3354931888 0.09688530630942335
+ vectorization 0.3564923362 0.1029495391940396
+ loop permutation 0.1394696203 0.040276695130403405
+ array packing 0.10807504670000001 0.031210422010018266
+ block caching 0.11121513170000001 0.03211723057489792
+ parallelization 0.1473262521 0.04254557033835026
@@ -1594,6 +1594,11 @@ 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 3.163 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 86af4530ea..8accce5737 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-5239ec05e9d248cbdd3f00dab713678cde7a6377
+af39b3441d13e6a672ea7a079b727e11252d267a
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 7cb14f3834..9305900d2a 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -590,7 +590,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.950 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 25.696 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 0198373b39..f599002e5c 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -444,7 +444,7 @@
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf99c1b85-012b-4980-be7f-9b3aefbd2168 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.zip71cd500c-0843-4e19-9c7f-d6fc3160bf08 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 982a5650f2..ca394ebaf7 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -454,14 +454,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 15%|#5 | 6.33M/41.5M [00:00<00:00, 49.3MB/s]
- 27%|##6 | 11.0M/41.5M [00:00<00:01, 30.5MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 31.1MB/s]
- 42%|####2 | 17.5M/41.5M [00:00<00:00, 29.9MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 34.1MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 39.7MB/s]
- 92%|#########2| 38.3M/41.5M [00:01<00:00, 30.7MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 33.7MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 36.2MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 33.3MB/s]
+ 42%|####2 | 17.5M/41.5M [00:00<00:00, 29.1MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 32.4MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 38.1MB/s]
+ 92%|#########2| 38.3M/41.5M [00:01<00:00, 39.2MB/s]
+100%|##########| 41.5M/41.5M [00:01<00:00, 36.7MB/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 bda965a9e6..f4f42f3683 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -437,11 +437,13 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 18%|#7 | 7.99M/44.7M [00:00<00:00, 56.6MB/s]
- 36%|###5 | 16.0M/44.7M [00:00<00:00, 61.3MB/s]
- 72%|#######1 | 32.0M/44.7M [00:00<00:00, 86.3MB/s]
- 90%|########9 | 40.1M/44.7M [00:00<00:00, 84.4MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 70.7MB/s]
+ 18%|#7 | 7.99M/44.7M [00:00<00:00, 76.7MB/s]
+ 34%|###4 | 15.3M/44.7M [00:00<00:00, 68.4MB/s]
+ 49%|####8 | 21.9M/44.7M [00:00<00:00, 58.1MB/s]
+ 67%|######6 | 29.8M/44.7M [00:00<00:00, 66.5MB/s]
+ 82%|########2 | 36.7M/44.7M [00:00<00:00, 68.4MB/s]
+ 97%|#########7| 43.4M/44.7M [00:00<00:00, 65.6MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 63.3MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index a6775ff128..b07b1443b9 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -657,7 +657,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.011 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 36.234 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 a45cafe668..f9b8ca73c3 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:56.534</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>07:13.150</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:33.011</p></td>
+<td><p>01:36.234</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:22.950</p></td>
+<td><p>01:25.696</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>00:56.989</p></td>
+<td><p>00:59.848</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:38.695</p></td>
+<td><p>00:40.261</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:32.820</p></td>
+<td><p>00:34.679</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>00:30.848</p></td>
+<td><p>00:31.763</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:28.464</p></td>
+<td><p>00:28.941</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:26.885</p></td>
+<td><p>00:27.505</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>00:23.139</p></td>
+<td><p>00:25.368</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>00:02.733</p></td>
+<td><p>00:02.854</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 e876b197c7..5cda3b4dad 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -799,7 +799,7 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 2558.9181 2558.5411 2562.7793 2557.7647 1.3580
+ 2752.1900 2751.4499 2755.9287 2749.9418 2.1244
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
diff --git a/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
index c808dc667b..782e1fda4f 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno_tvmc.html
@@ -443,25 +443,22 @@ to run this tutorial with a real device over rpc.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5
8192/102967424 [..............................] - ETA: 0s
- 7643136/102967424 [=>............................] - ETA: 0s
- 12689408/102967424 [==>...........................] - ETA: 0s
- 17350656/102967424 [====>.........................] - ETA: 0s
- 22708224/102967424 [=====>........................] - ETA: 0s
+ 8380416/102967424 [=>............................] - ETA: 0s
+ 16769024/102967424 [===>..........................] - ETA: 0s
+ 16908288/102967424 [===>..........................] - ETA: 1s
25157632/102967424 [======>.......................] - ETA: 0s
- 30605312/102967424 [=======>......................] - ETA: 0s
- 38526976/102967424 [==========>...................] - ETA: 0s
- 40189952/102967424 [==========>...................] - ETA: 0s
- 44130304/102967424 [===========>..................] - ETA: 0s
- 52625408/102967424 [==============>...............] - ETA: 0s
- 64823296/102967424 [=================>............] - ETA: 0s
- 67313664/102967424 [==================>...........] - ETA: 0s
- 74899456/102967424 [====================>.........] - ETA: 0s
- 79986688/102967424 [======================>.......] - ETA: 0s
- 83886080/102967424 [=======================>......] - ETA: 0s
- 89325568/102967424 [=========================>....] - ETA: 0s
+ 33546240/102967424 [========>.....................] - ETA: 0s
+ 38191104/102967424 [==========>...................] - ETA: 0s
+ 45080576/102967424 [============>.................] - ETA: 0s
+ 50323456/102967424 [=============>................] - ETA: 0s
+ 58654720/102967424 [================>.............] - ETA: 0s
+ 63725568/102967424 [=================>............] - ETA: 0s
+ 67100672/102967424 [==================>...........] - ETA: 0s
+ 72540160/102967424 [====================>.........] - ETA: 0s
+ 75202560/102967424 [====================>.........] - ETA: 0s
+ 84508672/102967424 [=======================>......] - ETA: 0s
+ 86073344/102967424 [========================>.....] - ETA: 0s
92266496/102967424 [=========================>....] - ETA: 0s
-100646912/102967424 [============================>.] - ETA: 0s
-102850560/102967424 [============================>.] - ETA: 0s
102967424/102967424 [==============================] - 1s 0us/step
</pre></div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 3fc6dd4850..5c09f43d50 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -667,7 +667,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.7801 15.7841 15.9218 15.6153 0.0960
+ 17.1162 17.1192 17.5817 16.3485 0.3853
</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 509b765be3..48460b4799 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -459,34 +459,35 @@ be unstable.</p>
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 4%|3 | 6.30M/170M [00:00<00:02, 60.4MB/s]
- 8%|7 | 13.0M/170M [00:00<00:02, 65.7MB/s]
- 11%|#1 | 19.2M/170M [00:00<00:03, 50.1MB/s]
- 14%|#4 | 24.3M/170M [00:00<00:03, 47.1MB/s]
- 18%|#7 | 30.3M/170M [00:00<00:02, 51.5MB/s]
- 22%|##1 | 37.3M/170M [00:00<00:02, 58.1MB/s]
- 25%|##5 | 43.1M/170M [00:00<00:02, 58.7MB/s]
- 29%|##8 | 48.9M/170M [00:00<00:02, 46.7MB/s]
- 33%|###2 | 56.0M/170M [00:01<00:02, 52.3MB/s]
- 37%|###6 | 62.3M/170M [00:01<00:02, 49.1MB/s]
- 40%|###9 | 67.3M/170M [00:01<00:02, 48.6MB/s]
- 42%|####2 | 72.1M/170M [00:01<00:02, 46.1MB/s]
- 47%|####7 | 80.0M/170M [00:01<00:01, 52.1MB/s]
- 51%|##### | 86.3M/170M [00:01<00:01, 52.3MB/s]
- 54%|#####3 | 91.4M/170M [00:01<00:01, 49.1MB/s]
- 57%|#####6 | 96.1M/170M [00:02<00:01, 44.3MB/s]
- 61%|###### | 103M/170M [00:02<00:01, 51.4MB/s]
- 64%|######3 | 108M/170M [00:02<00:01, 49.8MB/s]
- 67%|######6 | 113M/170M [00:02<00:01, 48.1MB/s]
- 69%|######9 | 118M/170M [00:02<00:01, 48.2MB/s]
- 72%|#######2 | 122M/170M [00:02<00:01, 38.7MB/s]
- 75%|#######5 | 128M/170M [00:02<00:01, 38.4MB/s]
- 80%|######## | 136M/170M [00:02<00:00, 43.9MB/s]
- 85%|########4 | 144M/170M [00:03<00:00, 48.2MB/s]
- 89%|########9 | 152M/170M [00:03<00:00, 47.2MB/s]
- 94%|#########4| 160M/170M [00:03<00:00, 49.8MB/s]
- 99%|#########8| 168M/170M [00:03<00:00, 56.9MB/s]
-100%|##########| 170M/170M [00:03<00:00, 50.3MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:04, 42.3MB/s]
+ 8%|8 | 14.3M/170M [00:00<00:03, 46.8MB/s]
+ 11%|#1 | 18.9M/170M [00:00<00:03, 44.7MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:03, 43.7MB/s]
+ 18%|#7 | 30.3M/170M [00:00<00:03, 39.9MB/s]
+ 20%|## | 34.2M/170M [00:00<00:03, 35.6MB/s]
+ 24%|##3 | 40.0M/170M [00:01<00:03, 41.6MB/s]
+ 28%|##8 | 48.0M/170M [00:01<00:02, 51.4MB/s]
+ 33%|###2 | 56.0M/170M [00:01<00:02, 46.1MB/s]
+ 36%|###5 | 60.8M/170M [00:01<00:02, 43.1MB/s]
+ 38%|###8 | 65.1M/170M [00:01<00:04, 25.6MB/s]
+ 42%|####2 | 72.0M/170M [00:02<00:03, 27.2MB/s]
+ 46%|####6 | 78.3M/170M [00:02<00:02, 32.2MB/s]
+ 48%|####8 | 82.1M/170M [00:02<00:02, 33.1MB/s]
+ 52%|#####1 | 88.0M/170M [00:02<00:02, 33.8MB/s]
+ 56%|#####5 | 94.3M/170M [00:02<00:02, 35.5MB/s]
+ 58%|#####7 | 98.0M/170M [00:02<00:02, 30.1MB/s]
+ 61%|######1 | 104M/170M [00:03<00:02, 29.5MB/s]
+ 66%|######5 | 112M/170M [00:03<00:01, 38.2MB/s]
+ 71%|####### | 120M/170M [00:03<00:01, 41.3MB/s]
+ 75%|#######5 | 128M/170M [00:03<00:00, 45.8MB/s]
+ 79%|#######9 | 134M/170M [00:03<00:01, 34.3MB/s]
+ 81%|########1 | 138M/170M [00:03<00:00, 34.2MB/s]
+ 85%|########4 | 144M/170M [00:04<00:00, 34.8MB/s]
+ 89%|########9 | 152M/170M [00:04<00:00, 38.7MB/s]
+ 94%|#########3| 159M/170M [00:04<00:00, 45.8MB/s]
+ 97%|#########6| 164M/170M [00:04<00:00, 41.7MB/s]
+ 99%|#########9| 168M/170M [00:04<00:00, 39.0MB/s]
+100%|##########| 170M/170M [00:04<00:00, 37.6MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode=& [...]
@@ -584,7 +585,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 37.665 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 57.182 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 d1ef3f6634..9b9aba802e 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -500,8 +500,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 35.4MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 48.5MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 71.2MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 73.3MB/s]
</pre></div>
</div>
</div>
@@ -592,7 +592,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3574 90.3433 90.8663 90.0979 0.1445
+ 90.8695 90.7012 99.6477 90.3184 1.0222
</pre></div>
</div>
<div class="admonition note">
@@ -631,7 +631,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.818 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.477 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 1fb5cfdaac..a027694eff 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -585,7 +585,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.9266 120.9304 122.1458 119.3036 0.4708
+ 121.5235 121.4552 126.0071 120.5605 0.6347
</pre></div>
</div>
<div class="admonition note">
@@ -613,7 +613,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 40.023 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 32.560 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 9388305ff6..edc7ac018f 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -526,7 +526,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 43.356 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 47.629 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 2ea1939ff4..105c8bf79e 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -468,23 +468,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 1%|1 | 1331/132723 [00:00<00:09, 13179.86KB/s]
- 3%|3 | 4243/132723 [00:00<00:05, 22480.18KB/s]
- 8%|7 | 10614/132723 [00:00<00:02, 41245.65KB/s]
- 15%|#4 | 19323/132723 [00:00<00:01, 59306.31KB/s]
- 21%|##1 | 28084/132723 [00:00<00:01, 69498.00KB/s]
- 28%|##7 | 36873/132723 [00:00<00:01, 75743.83KB/s]
- 35%|###4 | 45803/132723 [00:00<00:01, 80169.49KB/s]
- 41%|####1 | 54648/132723 [00:00<00:00, 82801.16KB/s]
- 48%|####7 | 63499/132723 [00:00<00:00, 84583.76KB/s]
- 55%|#####4 | 72437/132723 [00:01<00:00, 86060.90KB/s]
- 61%|######1 | 81299/132723 [00:01<00:00, 86834.87KB/s]
- 68%|######7 | 90111/132723 [00:01<00:00, 87224.18KB/s]
- 75%|#######4 | 98994/132723 [00:01<00:00, 87708.56KB/s]
- 81%|########1 | 107822/132723 [00:01<00:00, 87879.02KB/s]
- 88%|########7 | 116664/132723 [00:01<00:00, 88034.69KB/s]
- 95%|#########4| 125468/132723 [00:01<00:00, 87954.46KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 78681.29KB/s]
+ 1%| | 1148/132723 [00:00<00:11, 11448.78KB/s]
+ 3%|2 | 3736/132723 [00:00<00:06, 19809.98KB/s]
+ 7%|7 | 9412/132723 [00:00<00:03, 36615.78KB/s]
+ 13%|#3 | 17848/132723 [00:00<00:02, 55415.05KB/s]
+ 20%|#9 | 26262/132723 [00:00<00:01, 65755.58KB/s]
+ 26%|##6 | 34784/132723 [00:00<00:01, 72365.04KB/s]
+ 33%|###2 | 43328/132723 [00:00<00:01, 76634.94KB/s]
+ 39%|###9 | 51894/132723 [00:00<00:01, 79504.00KB/s]
+ 45%|####5 | 60366/132723 [00:00<00:00, 81131.30KB/s]
+ 52%|#####1 | 68871/132723 [00:01<00:00, 82338.35KB/s]
+ 58%|#####8 | 77436/132723 [00:01<00:00, 83348.29KB/s]
+ 65%|######4 | 85772/132723 [00:01<00:00, 69368.04KB/s]
+ 71%|#######1 | 94326/132723 [00:01<00:00, 73661.32KB/s]
+ 77%|#######6 | 102024/132723 [00:01<00:00, 55606.34KB/s]
+ 83%|########3 | 110551/132723 [00:01<00:00, 62325.90KB/s]
+ 89%|########8 | 117599/132723 [00:01<00:00, 63411.43KB/s]
+ 95%|#########4| 126029/132723 [00:01<00:00, 68760.21KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 67112.08KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -523,7 +524,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 59.144 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 10.919 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 5cf459e97f..09ed669bad 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>16:47.218</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>17:28.304</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -354,43 +354,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:59.144</p></td>
+<td><p>04:10.919</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>03:37.665</p></td>
+<td><p>03:57.182</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>02:40.023</p></td>
+<td><p>02:32.560</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:43.356</p></td>
+<td><p>01:47.629</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:17.818</p></td>
+<td><p>01:21.477</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_adreno.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno™</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno.py</span></code>)</p></td>
-<td><p>00:55.481</p></td>
+<td><p>00:59.077</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_adreno_tvmc.html#sphx-glr-how-to-deploy-models-deploy-model-on-adreno-tvmc-py"><span class="std std-ref">Deploy the Pretrained Model on Adreno™ with tvmc Interface</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_adreno_tvmc.py</span></code>)</p></td>
-<td><p>00:52.112</p></td>
+<td><p>00:53.901</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:43.673</p></td>
+<td><p>00:46.049</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:29.292</p></td>
+<td><p>00:30.070</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:28.649</p></td>
+<td><p>00:29.432</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index b5fe402cef..ef49d35408 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -624,7 +624,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip44b787e6-68dc-44b3-ba48-7ecf045ac893 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.zip7636ec96-a624-4e9f-8b4e-c1e7120f818b 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 4195a67040..fd864b94e9 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:55.245</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:57.915</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,19 +354,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:51.380</p></td>
+<td><p>00:53.840</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>00:02.784</p></td>
+<td><p>00:02.925</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>00:01.074</p></td>
+<td><p>00:01.143</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index cca917a0c0..2767e5b739 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -531,10 +531,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 23061us [23061us] (48.72%; 48.72%)
-FoldScaleAxis: 24273us [10us] (51.28%; 51.28%)
- FoldConstant: 24264us [1756us] (51.26%; 99.96%)
- InferType: 22507us [22507us] (47.55%; 92.76%)
+InferType: 23476us [23476us] (48.28%; 48.28%)
+FoldScaleAxis: 25152us [9us] (51.72%; 51.72%)
+ FoldConstant: 25143us [1770us] (51.70%; 99.96%)
+ InferType: 23373us [23373us] (48.06%; 92.96%)
</pre></div>
</div>
</div>
@@ -556,10 +556,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 22352us [22352us] (47.49%; 47.49%)
-FoldScaleAxis: 24719us [7us] (52.51%; 52.51%)
- FoldConstant: 24712us [1821us] (52.50%; 99.97%)
- InferType: 22891us [22891us] (48.63%; 92.63%)
+InferType: 22887us [22887us] (48.07%; 48.07%)
+FoldScaleAxis: 24728us [8us] (51.93%; 51.93%)
+ FoldConstant: 24721us [1868us] (51.92%; 99.97%)
+ InferType: 22853us [22853us] (48.00%; 92.44%)
</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 4ecbb138ab..f686a8fa63 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -580,7 +580,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.283519 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 53.515617 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 b47b2a7457..b652fc1ffc 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -862,7 +862,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 11.150541 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 12.236822 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 6847c30363..bfefeed769 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -477,8 +477,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018940
-Baseline: 3.198221
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019959
+Baseline: 3.471027
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -537,7 +537,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.290675
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.339590
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -594,7 +594,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.339132
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.359948
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -649,7 +649,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118303
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.145167
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -726,7 +726,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110241
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111442
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -804,7 +804,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111996
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.113196
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -884,7 +884,7 @@ class Module:
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147561
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.149567
</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 853c85c511..c5748f8be5 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.824</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:37.205</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,15 +354,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.823</p></td>
+<td><p>00:33.990</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>00:01.863</p></td>
+<td><p>00:02.000</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>00:01.138</p></td>
+<td><p>00:01.215</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 935aaa2290..8d8808d6f5 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:09.517</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>10:38.302</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -354,27 +354,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>06:13.990</p></td>
+<td><p>06:33.263</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>01:43.127</p></td>
+<td><p>01:47.091</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>01:11.538</p></td>
+<td><p>01:14.351</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:32.857</p></td>
+<td><p>00:34.063</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>00:15.032</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>00:13.750</p></td>
+<td><p>00:14.501</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 8a1f0e7245..7214be82f7 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -510,500 +510,479 @@ class Module:
@T.prim_func
def main(data: T.Buffer((1, 512, 7, 7), "float32"), kernel: T.Buffer((512, 512, 3, 3), "float32"), bias: T.Buffer((1, 512, 1, 1), "float32"), compute: T.Buffer((1, 512, 7, 7), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- blockIdx_x = T.launch_thread("blockIdx.x", 8)
- conv2d_nchw = T.allocate([28], "float32", "local")
- pad_temp_shared = T.allocate([1296], "float32", "shared")
- kernel_shared = T.allocate([9216], "float32", "shared")
- threadIdx_x = T.launch_thread("threadIdx.x", 112)
- conv2d_nchw_1 = T.Buffer((196,), data=conv2d_nchw, scope="local", align=32)
+ blockIdx_x = T.launch_thread("blockIdx.x", 28)
+ conv2d_nchw = T.allocate([14], "float32", "local")
+ pad_temp_shared = T.allocate([72], "float32", "shared")
+ kernel_shared = T.allocate([3072], "float32", "shared")
+ threadIdx_x = T.launch_thread("threadIdx.x", 64)
+ conv2d_nchw_1 = T.Buffer((14,), data=conv2d_nchw, scope="local", align=32)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[14] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
- conv2d_nchw_1[15] = T.float32(0)
conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[16] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
- conv2d_nchw_1[17] = T.float32(0)
conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[18] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
- conv2d_nchw_1[19] = T.float32(0)
conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[20] = T.float32(0)
conv2d_nchw_1[7] = T.float32(0)
- conv2d_nchw_1[21] = T.float32(0)
conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[22] = T.float32(0)
conv2d_nchw_1[9] = T.float32(0)
- conv2d_nchw_1[23] = T.float32(0)
conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[24] = T.float32(0)
conv2d_nchw_1[11] = T.float32(0)
- conv2d_nchw_1[25] = T.float32(0)
conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[26] = T.float32(0)
conv2d_nchw_1[13] = T.float32(0)
- conv2d_nchw_1[27] = T.float32(0)
- for rc_outer_outer in range(32):
- cse_var_2: T.int32 = rc_outer_outer * 784
- cse_var_1: T.int32 = rc_outer_outer * 144
+ for rc_outer_outer, ry_outer_outer in T.grid(64, 3):
+ cse_var_2: T.int32 = rc_outer_outer * 72
+ cse_var_1: T.int32 = ry_outer_outer * 3
+ pad_temp_shared_1 = T.Buffer((72,), data=pad_temp_shared, scope="shared")
+ with T.launch_thread("threadIdx.x", 64) as threadIdx_x_1:
+ data_1 = T.Buffer((25088,), data=data.data)
+ if T.likely(threadIdx_x_1 < 18):
+ pad_temp_shared_1[threadIdx_x_1 * 4] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= threadIdx_x_1 * 4 % 9 and threadIdx_x_1 * 4 % 9 < 8, data_1[rc_outer_outer * 392 + threadIdx_x_1 * 4 // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + threadIdx_x_1 * 4 % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 18):
+ pad_temp_shared_1[threadIdx_x_1 * 4 + 1] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 1) % 9 and (threadIdx_x_1 * 4 + 1) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 1) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 1) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 18):
+ pad_temp_shared_1[threadIdx_x_1 * 4 + 2] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 2) % 9 and (threadIdx_x_1 * 4 + 2) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 2) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 2) % 9 - 8], T.float32(0))
+ if T.likely(threadIdx_x_1 < 18):
+ pad_temp_shared_1[threadIdx_x_1 * 4 + 3] = T.if_then_else(1 <= ry_outer_outer + blockIdx_x % 7 and ry_outer_outer + blockIdx_x % 7 < 8 and 1 <= (threadIdx_x_1 * 4 + 3) % 9 and (threadIdx_x_1 * 4 + 3) % 9 < 8, data_1[rc_outer_outer * 392 + (threadIdx_x_1 * 4 + 3) // 9 * 49 + ry_outer_outer * 7 + blockIdx_x % 7 * 7 + (threadIdx_x_1 * 4 + 3) % 9 - 8], T.float32(0))
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.Buffer((1296,), 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] = 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[cse_var_2 + threadIdx_x_1 // 81 * 49 + threadIdx_x_1 % 81 // 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 112] = T.if_then_else(9 <= (threadIdx_x_1 + 31) % 81 and (threadIdx_x_1 + 31) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 112) // 81 * 49 + (threadIdx_x_1 + 31) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 224] = T.if_then_else(9 <= (threadIdx_x_1 + 62) % 81 and (threadIdx_x_1 + 62) % 81 < 72 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 224) // 81 * 49 + (threadIdx_x_1 + 62) % 81 // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 336] = T.if_then_else(9 <= (threadIdx_x_1 + 12) % 81 and (threadIdx_x_1 + 12) % 81 < 72 and 1 <= (threadIdx_x_1 + 3) % 9 and (threadIdx_x_1 + 3) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 336) // 81 * 49 + (threadIdx_x_1 + 12) % 81 // 9 * 7 + (threadIdx_x_1 + 3) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 448] = T.if_then_else(9 <= (threadIdx_x_1 + 43) % 81 and (threadIdx_x_1 + 43) % 81 < 72 and 1 <= (threadIdx_x_1 + 7) % 9 and (threadIdx_x_1 + 7) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 448) // 81 * 49 + (threadIdx_x_1 + 43) % 81 // 9 * 7 + (threadIdx_x_1 + 7) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 560] = T.if_then_else(9 <= (threadIdx_x_1 + 74) % 81 and (threadIdx_x_1 + 74) % 81 < 72 and 1 <= (threadIdx_x_1 + 2) % 9 and (threadIdx_x_1 + 2) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 560) // 81 * 49 + (threadIdx_x_1 + 74) % 81 // 9 * 7 + (threadIdx_x_1 + 2) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 672] = T.if_then_else(9 <= (threadIdx_x_1 + 24) % 81 and (threadIdx_x_1 + 24) % 81 < 72 and 1 <= (threadIdx_x_1 + 6) % 9 and (threadIdx_x_1 + 6) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 672) // 81 * 49 + (threadIdx_x_1 + 24) % 81 // 9 * 7 + (threadIdx_x_1 + 6) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 784] = T.if_then_else(9 <= (threadIdx_x_1 + 55) % 81 and (threadIdx_x_1 + 55) % 81 < 72 and 1 <= (threadIdx_x_1 + 1) % 9 and (threadIdx_x_1 + 1) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 784) // 81 * 49 + (threadIdx_x_1 + 55) % 81 // 9 * 7 + (threadIdx_x_1 + 1) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 896] = T.if_then_else(9 <= (threadIdx_x_1 + 5) % 81 and (threadIdx_x_1 + 5) % 81 < 72 and 1 <= (threadIdx_x_1 + 5) % 9 and (threadIdx_x_1 + 5) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 896) // 81 * 49 + (threadIdx_x_1 + 5) % 81 // 9 * 7 + (threadIdx_x_1 + 5) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 1008] = T.if_then_else(1 <= (threadIdx_x_1 // 9 + 4) % 9 and (threadIdx_x_1 + 36) % 81 < 72 and 1 <= threadIdx_x_1 % 9 and threadIdx_x_1 % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1008) // 81 * 49 + (threadIdx_x_1 // 9 + 4) % 9 * 7 + threadIdx_x_1 % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- pad_temp_shared_1[threadIdx_x_1 + 1120] = T.if_then_else(9 <= (threadIdx_x_1 + 67) % 81 and (threadIdx_x_1 + 67) % 81 < 72 and 1 <= (threadIdx_x_1 + 4) % 9 and (threadIdx_x_1 + 4) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1120) // 81 * 49 + (threadIdx_x_1 + 67) % 81 // 9 * 7 + (threadIdx_x_1 + 4) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 112):
- if T.likely(threadIdx_x_1 < 64):
- pad_temp_shared_1[threadIdx_x_1 + 1232] = T.if_then_else(threadIdx_x_1 < 55 and 1 <= (threadIdx_x_1 + 8) % 9 and (threadIdx_x_1 + 8) % 9 < 8, data_1[cse_var_2 + (threadIdx_x_1 + 1232) // 81 * 49 + (threadIdx_x_1 + 17) // 9 * 7 + (threadIdx_x_1 + 8) % 9 - 8], T.float32(0))
- threadIdx_x_2 = T.env_thread("threadIdx.x")
- kernel_shared_1 = T.Buffer((9216,), 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, 112):
- kernel_shared_1[threadIdx_x_2] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 112] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 112) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 224] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 224) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 336] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 336) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 448] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 448) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 560] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 560) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 672) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 784] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 784) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 896] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 896) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1008] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 32256]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1120] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1120) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1232] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1232) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1344] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1344) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1456] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1456) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1568] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1568) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1680] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1680) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1792] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1792) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 1904] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 1904) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2016] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 64512]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2128] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2128) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2240] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2240) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2352] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2352) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2464] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2464) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2576] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2576) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2688] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2688) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2800] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2800) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 2912] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 2912) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3024] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 96768]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3136] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3136) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3248] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3248) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3360] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3360) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3472] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3472) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3584] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3584) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3696] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3696) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3808] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3808) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 3920] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 3920) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4032] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 129024]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4144] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4144) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4256] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4256) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4368] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4368) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4480] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4480) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4592] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4592) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4704] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4704) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4816] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4816) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 4928] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 4928) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5040] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 161280]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5152] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5152) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5264] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5264) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5376] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5376) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5488] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5488) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5600] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5600) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5712] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5712) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5824] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5824) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 5936] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 5936) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6048] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 193536]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6160] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6160) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6272] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6272) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6384] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6384) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6496] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6496) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6608] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6608) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6720] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6720) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6832] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6832) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 6944] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 6944) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7056] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 225792]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7168] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7168) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7280] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7280) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7392] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7392) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7504] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7504) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7616] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7616) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7728] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7728) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7840] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7840) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 7952] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 7952) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8064] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 258048]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8176] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8176) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 112) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8288] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8288) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 80) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8400] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8400) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 48) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8512] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8512) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 16]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8624] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8624) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 128) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8736] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8736) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 96) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8848] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8848) // 144 * 4608 + cse_var_1 + (threadIdx_x_2 + 64) % 144]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 8960] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 8960) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 32]
- with T.launch_thread(threadIdx_x_2, 112):
- kernel_shared_1[threadIdx_x_2 + 9072] = kernel_1[blockIdx_x * 294912 + cse_var_1 + threadIdx_x_2 + 290304]
- with T.launch_thread(threadIdx_x_2, 112):
- if T.likely(threadIdx_x_2 < 32):
- kernel_shared_1[threadIdx_x_2 + 9184] = kernel_1[blockIdx_x * 294912 + (threadIdx_x_2 + 9184) // 144 * 4608 + cse_var_1 + threadIdx_x_2 + 112]
- for rc_inner in range(16):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4608]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 144]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4752]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 1]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4609]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 1] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 145]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4753]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 2]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4610]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 2] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 146]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4754]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 3]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4611]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 9] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 147]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4755]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4612]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 10] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 148]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4756]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 5]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4613]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 11] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 149]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4757]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 6]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4614]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 18] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 27] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 36] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 45] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 54] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 63] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 150]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 72] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4758]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 7]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4615]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 19] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 28] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 37] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 46] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 55] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 64] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 151]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 73] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4759]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 8]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4616]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 20] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 29] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 38] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 47] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 56] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 65] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 152]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_inner * 81 + threadIdx_x % 7 + 74] * kernel_shared_1[threadIdx_x // 7 * 288 + rc_inner * 9 + 4760]
- for i1_inner, i2_inner in T.grid(2, 7):
- cse_var_3: T.int32 = i1_inner * 7 + i2_inner
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 64) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 64) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 128) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 128) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 192] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 36864]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 256) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 256) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 320) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 320) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 384] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 73728]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 448) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 448) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 512) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 512) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 576] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 110592]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 640) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 640) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 704) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 704) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 768] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 147456]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 832) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 832) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 896) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 896) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 960] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 184320]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1024) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1024) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1088) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1088) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1152] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 221184]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1216) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1216) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1280) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1280) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1344] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 258048]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1408) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1408) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1472) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1472) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1536] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 294912]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1600) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1600) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1664) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1664) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1728] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 331776]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1792) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1792) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1856) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1856) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 1920] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 368640]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 1984) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 1984) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2048) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2048) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2112] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 405504]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2176) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2176) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2240) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2240) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2304] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 442368]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2368) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2368) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2432) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2432) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2496] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 479232]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2560) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2560) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2624) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2624) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2688] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 516096]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2752) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2752) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2816) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2816) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[threadIdx_x_1 + 2880] = kernel_1[blockIdx_x // 7 * 589824 + threadIdx_x_1 // 24 * 4608 + cse_var_2 + threadIdx_x_1 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_1 % 3 + 552960]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 2944) // 24 * 24 + (threadIdx_x_1 + 16) % 24 // 3 * 3 + (threadIdx_x_1 + 1) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 2944) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 1) % 3]
+ with T.launch_thread(threadIdx_x_1, 64):
+ kernel_shared_1[(threadIdx_x_1 + 3008) // 24 * 24 + (threadIdx_x_1 + 8) % 24 // 3 * 3 + (threadIdx_x_1 + 2) % 3] = kernel_1[blockIdx_x // 7 * 589824 + (threadIdx_x_1 + 3008) // 24 * 4608 + cse_var_2 + (threadIdx_x_1 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_1 + 2) % 3]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 3]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[0] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[9] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 24]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 27]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 1]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 4]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[1] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[10] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 25]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 28]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 2]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 5]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[2] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[11] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[3] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[12] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[4] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[13] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[5] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[14] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[6] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[15] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[7] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[16] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[8] * kernel_shared_1[threadIdx_x * 48 + 26]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[17] * kernel_shared_1[threadIdx_x * 48 + 29]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 6]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 9]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[18] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[27] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 30]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 33]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 7]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 10]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[19] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[28] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 31]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 34]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 8]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 11]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[20] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[29] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[21] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[30] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[22] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[31] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[23] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[32] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[24] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[33] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[25] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[34] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[26] * kernel_shared_1[threadIdx_x * 48 + 32]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[35] * kernel_shared_1[threadIdx_x * 48 + 35]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 12]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 15]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[36] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[45] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 36]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 39]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 13]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 16]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[37] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[46] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 37]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 40]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 14]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 17]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[38] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[47] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[39] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[48] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[40] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[49] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[41] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[50] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[42] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[51] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[43] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[52] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[44] * kernel_shared_1[threadIdx_x * 48 + 38]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[53] * kernel_shared_1[threadIdx_x * 48 + 41]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 18]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 21]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[54] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[63] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 42]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 45]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 19]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 22]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[55] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[64] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 43]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 46]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 20]
+ conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 23]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[56] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[65] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[57] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[66] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[58] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[67] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[59] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[68] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[60] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[69] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[61] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[70] * kernel_shared_1[threadIdx_x * 48 + 47]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[62] * kernel_shared_1[threadIdx_x * 48 + 44]
+ conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[71] * kernel_shared_1[threadIdx_x * 48 + 47]
+ for i1_inner, i3_inner in T.grid(2, 7):
compute_1 = T.Buffer((25088,), data=compute.data)
bias_1 = T.Buffer((512,), data=bias.data)
- compute_1[blockIdx_x * 3136 + threadIdx_x // 7 * 98 + i1_inner * 49 + i2_inner * 7 + threadIdx_x % 7] = T.max(conv2d_nchw_1[cse_var_3] + bias_1[blockIdx_x * 64 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_1[blockIdx_x * 3136 + threadIdx_x // 7 * 98 + i1_inner * 49 + i2_inner * 7 + threadIdx_x % 7 + 1568] = T.max(conv2d_nchw_1[cse_var_3 + 14] + bias_1[blockIdx_x * 64 + threadIdx_x // 7 * 2 + i1_inner + 32], T.float32(0))
+ compute_1[blockIdx_x // 7 * 6272 + threadIdx_x * 98 + i1_inner * 49 + blockIdx_x % 7 * 7 + i3_inner] = T.max(conv2d_nchw_1[i1_inner * 7 + i3_inner] + bias_1[blockIdx_x // 7 * 128 + threadIdx_x * 2 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -1037,7 +1016,7 @@ 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: 0.360 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.342 ms
</pre></div>
</div>
</div>
@@ -1066,36 +1045,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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=7)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_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_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_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)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=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=7)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1115,12 +1094,12 @@ 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=112)
+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=64)
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=4)
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=112)
+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=64)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -1147,399 +1126,429 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-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[28];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[9216];
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[21] = 0.000000e+00f;
conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[22] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[23] = 0.000000e+00f;
conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[24] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[25] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[26] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[27] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- __syncthreads();
- 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 * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((9 <= ((((int)threadIdx.x) + 24) % 81)) && (((((int)threadIdx.x) + 24) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 672) / 81) * 49)) + ((((((int)threadIdx.x) + 24) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 896)] = (((((9 <= ((((int)threadIdx.x) + 5) % 81)) && (((((int)threadIdx.x) + 5) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 81) * 49)) + ((((((int)threadIdx.x) + 5) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1008)] = (((((1 <= (((((int)threadIdx.x) / 9) + 4) % 9)) && (((((int)threadIdx.x) + 36) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1008) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 4) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1120)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1120) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 64) {
- pad_temp_shared[(((int)threadIdx.x) + 1232)] = ((((((int)threadIdx.x) < 55) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1232) / 81) * 49)) + (((((int)threadIdx.x) + 17) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 112) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 224) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 336) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 448) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 560) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 672) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 896) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1120) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1232) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1344) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1456) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1680) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1792) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 1904) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2128) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2240) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2352) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2464) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2576) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2688) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2800) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 2912) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3136) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3248)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3248) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3360) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3472)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3472) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3584) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3696)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3696) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3808) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 3920) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 4144)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4144) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4256) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4368)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4368) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4480) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 4592)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4592) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4704) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4816)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4816) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 4928)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 4928) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 5040)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 161280)];
- kernel_shared[(((int)threadIdx.x) + 5152)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5152) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5264)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5264) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5376) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5488)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5488) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 5600)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5600) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5712)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5712) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5824)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5824) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 5936)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 5936) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 6048)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 193536)];
- kernel_shared[(((int)threadIdx.x) + 6160)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6160) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6272) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6384)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6384) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6496)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6496) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 6608)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6608) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6720)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6720) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6832)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6832) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 6944)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 6944) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 7056)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 225792)];
- kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7168) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7280)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7280) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7392)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7504)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7504) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 7616)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7616) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7728)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7728) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7840)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7840) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 7952)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 7952) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 258048)];
- kernel_shared[(((int)threadIdx.x) + 8176)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 112) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8288)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8288) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 80) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8400)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8400) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 48) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8512)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8512) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 16)];
- kernel_shared[(((int)threadIdx.x) + 8624)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8624) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8736)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8736) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 96) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8848)] = kernel[((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8848) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 8960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 32)];
- kernel_shared[(((int)threadIdx.x) + 9072)] = kernel[((((((int)blockIdx.x) * 294912) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 290304)];
- if (((int)threadIdx.x) < 32) {
- kernel_shared[(((int)threadIdx.x) + 9184)] = kernel[(((((((int)blockIdx.x) * 294912) + (((((int)threadIdx.x) + 9184) / 144) * 4608)) + (rc_outer_outer * 144)) + ((int)threadIdx.x)) + 112)];
- }
- __syncthreads();
- for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9))]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4608)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[((rc_inner * 81) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4752)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4609)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4753)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4610)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4754)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4611)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4755)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4612)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4756)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4613)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4757)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4614)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4758)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4615)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4759)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4616)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_inner * 81) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 288) + (rc_inner * 9)) + 4760)]));
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 64) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 128) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((((((int)threadIdx.x) + 256) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 320) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((((((int)threadIdx.x) + 448) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 512) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((((((int)threadIdx.x) + 640) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 704) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((((((int)threadIdx.x) + 832) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 896) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((((((int)threadIdx.x) + 1024) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1088) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((((((int)threadIdx.x) + 1216) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1280) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((((((int)threadIdx.x) + 1408) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1472) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((((((int)threadIdx.x) + 1600) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1664) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((((((int)threadIdx.x) + 1792) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 1856) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((((((int)threadIdx.x) + 1984) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2048) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((((((int)threadIdx.x) + 2176) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2240) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((((((int)threadIdx.x) + 2368) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2432) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((((((int)threadIdx.x) + 2560) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2624) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((((((int)threadIdx.x) + 2752) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 2816) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((((((int)threadIdx.x) + 2944) / 24) * 24) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((((((int)threadIdx.x) + 3008) / 24) * 24) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) * 3136) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 1568)] = max((conv2d_nchw[(((i1_inner * 7) + i2_inner) + 14)] + bias[((((((int)blockIdx.x) * 64) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 32)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
}
@@ -1575,7 +1584,7 @@ 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 13.990 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 33.263 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 7f87a621cd..721115017e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -921,7 +921,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 8.0991 8.0963 8.1155 8.0854 0.0124
+ 8.1076 8.1102 8.1201 8.0926 0.0114
</pre></div>
</div>
</div>
@@ -943,7 +943,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.538 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.351 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 1a31d0bfe4..aba06124f2 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -940,7 +940,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 752.8227 753.6648 754.0578 750.7456 1.4775
+ 771.7696 772.9308 774.5017 767.8764 2.8266
</pre></div>
</div>
</div>
@@ -962,7 +962,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 43.127 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 47.091 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 862e082c6b..188902cc3c 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -637,75 +637,26 @@ class Module:
@T.prim_func
def main(placeholder: T.Buffer((128, 256), "float32"), placeholder_1: T.Buffer((4916, 16, 1), "float32"), placeholder_2: T.Buffer((4916,), "int32"), placeholder_3: T.Buffer((33,), "int32"), placeholder_4: T.Buffer((128, 512), "float32"), compute: T.Buffer((128, 512), "float32")):
T.func_attr({"from_legacy_te_schedule": T.bool(True), "global_symbol": "main", "tir.noalias": T.bool(True)})
- for i0_outer in T.parallel(2):
+ for i0_outer_i1_outer_fused in T.parallel(32):
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(placeholder_5[cse_var_2 + 1] - placeholder_5[cse_var_2], where={cse_var_2: i1_outer * 2 + nb_j_inner}), 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))
+ compute_2 = T.Buffer((2048,), data=compute_1)
+ for i_outer_inner, nb_j_inner in T.grid(8, 2):
+ for i_inner_init, j_init in T.grid(8, 16):
+ compute_2[i_outer_inner * 256 + i_inner_init * 32 + nb_j_inner * 16 + j_init] = T.float32(0)
+ for elem_idx, i_inner, j in T.grid(T.Let(placeholder_5[cse_var_1 + 1] - placeholder_5[cse_var_1], where={cse_var_1: i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner}), 8, 16):
+ cse_var_1 = T.int32()
+ placeholder_5 = T.Buffer((33,), "int32", data=placeholder_3.data)
+ cse_var_3: T.int32 = i0_outer_i1_outer_fused % 16 * 2 + nb_j_inner
+ cse_var_2: T.int32 = i_outer_inner * 256 + i_inner * 32 + nb_j_inner * 16 + j
+ placeholder_6 = T.Buffer((78656,), data=placeholder_1.data)
+ placeholder_7 = T.Buffer((32768,), data=placeholder.data)
+ placeholder_8 = T.Buffer((4916,), "int32", data=placeholder_2.data)
+ compute_2[cse_var_2] = compute_2[cse_var_2] + placeholder_6[placeholder_5[cse_var_3] * 16 + elem_idx * 16 + j] * T.max(placeholder_7[i0_outer_i1_outer_fused // 16 * 16384 + i_outer_inner * 2048 + i_inner * 256 + placeholder_8[placeholder_5[cse_var_3] + elem_idx]], T.float32(0))
+ for i0_inner, i1_inner in T.grid(64, 32):
+ cse_var_4: T.int32 = i0_outer_i1_outer_fused // 16 * 32768 + i0_inner * 512 + i0_outer_i1_outer_fused % 16 * 32 + i1_inner
+ compute_3 = T.Buffer((65536,), data=compute.data)
+ placeholder_5 = T.Buffer((65536,), data=placeholder_4.data)
+ compute_3[cse_var_4] = T.max(compute_2[i0_inner * 32 + i1_inner] + placeholder_5[cse_var_4], T.float32(0))
</pre></div>
</div>
</div>
@@ -739,7 +690,7 @@ class Module:
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.802 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.590 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 80877a540d..15aabbf0fb 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:47.201</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:35.347</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,11 +354,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:47.166</p></td>
+<td><p>00:35.312</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.022</p></td>
+<td><p>00:00.021</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
@@ -366,7 +366,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
-<td><p>00:00.004</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
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 3b4b2b5263..93076f7d03 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -695,7 +695,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 256]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2388758
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3568698
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
@@ -818,9 +818,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6798376
-No: 3 GFLOPS: 9.40/9.40 result: MeasureResult(costs=(0.024635136833333335,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.562204360961914, timestamp=1680803428.0066042) [('tile_f', [-1, 8, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8009137
-No: 4 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,769270
+No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -942,8 +941,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9133037
-No: 5 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1302615
+No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1065,8 +1064,8 @@ 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, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2321242
-No: 6 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7311343
+No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1188,8 +1187,8 @@ 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, 8, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6808465
-No: 7 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 8, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5585613
+No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1311,8 +1310,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9317402
-No: 8 GFLOPS: 0.00/9.40 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4568449
+No: 7 GFLOPS: 7.98/7.98 result: MeasureResult(costs=(0.02902224725,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.405341386795044, timestamp=1680811582.5334728) [('tile_f', [-1, 2, 8, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3968262
+No: 8 GFLOPS: 0.00/7.98 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1434,9 +1434,8 @@ 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, 2, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4065594
-No: 9 GFLOPS: 9.48/9.48 result: MeasureResult(costs=(0.02441596216666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=9.508664846420288, timestamp=1680803440.8370838) [('tile_f', [-1, 2, 2, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4849211
-No: 10 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8567258
+No: 9 GFLOPS: 0.00/7.98 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
@@ -1558,8 +1557,9 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 16, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10083769
-No: 11 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 128]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6937915
+No: 10 GFLOPS: 112.40/112.40 result: MeasureResult(costs=(0.002059589918367347,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.452477216720581, timestamp=1680811584.1773179) [('tile_f', [-1, 1, 32, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 16]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5740500
+No: 11 GFLOPS: 0.00/112.40 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
@@ -1681,8 +1681,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2491385
-No: 12 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2563414
+No: 12 GFLOPS: 0.00/112.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1804,8 +1804,10 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 2, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5566086
-No: 13 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 4, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,958618
+No: 13 GFLOPS: 230.73/230.73 result: MeasureResult(costs=(0.0010033478562091504,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6993286609649658, timestamp=1680811587.3408077) [('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4073430
+No: 14 GFLOPS: 19.77/230.73 result: MeasureResult(costs=(0.011709251333333334,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.626004457473755, timestamp=1680811588.2659273) [('tile_f', [-1, 32, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7755060
+No: 15 GFLOPS: 0.00/230.73 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1927,8 +1929,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2708616
-No: 14 GFLOPS: 0.00/9.48 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3240986
+No: 16 GFLOPS: 0.00/230.73 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
@@ -2050,9 +2052,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7391189
-No: 15 GFLOPS: 175.28/175.28 result: MeasureResult(costs=(0.00132072,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.587515115737915, timestamp=1680803445.678157) [('tile_f', [-1, 1, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8567099
-No: 16 GFLOPS: 0.00/175.28 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2001396
+No: 17 GFLOPS: 0.00/230.73 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2174,8 +2175,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 64, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8036476
-No: 17 GFLOPS: 0.00/175.28 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 32, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10147151
+No: 18 GFLOPS: 0.00/230.73 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -2297,9 +2298,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7213737
-No: 18 GFLOPS: 26.18/175.28 result: MeasureResult(costs=(0.008842506333333335,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6490862369537354, timestamp=1680803447.536689) [('tile_f', [-1, 4, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5488705
-No: 19 GFLOPS: 0.00/175.28 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4530870
+No: 19 GFLOPS: 0.00/230.73 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
@@ -2421,8 +2421,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 1, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9905664
-No: 20 GFLOPS: 0.00/175.28 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7515826
+No: 20 GFLOPS: 0.00/230.73 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
@@ -2544,7 +2544,7 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 16, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7846483
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5358497
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2583,9 +2583,9 @@ 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, 8, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 8, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8567099
+[('tile_f', [-1, 1, 32, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4073430
Finish loading 20 records
-Time cost of this operator: 0.001716
+Time cost of this operator: 0.001413
</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 477d55d6be..fde24354ef 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -649,10 +649,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.3 98.748 (1, 2, 10, 10, 3) 2 1 [316.3]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.95 (1, 6, 10, 10) 1 1 [3.042]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.969 0.303 (1, 1, 10, 10, 3) 1 1 [0.969]
-Total_time - 320.311 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.5 98.739 (1, 2, 10, 10, 3) 2 1 [313.5]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.042 0.958 (1, 6, 10, 10) 1 1 [3.042]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 0.303 (1, 1, 10, 10, 3) 1 1 [0.962]
+Total_time - 317.504 - - - - -
</pre></div>
</div>
</div>
@@ -704,13 +704,13 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 107.2 97.628 (1, 6, 10, 10, 1) 2 1 [107.2]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.765 1.607 (1, 6, 10, 10) 1 1 [1.765]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.839 0.764 (1, 3, 10, 10, 1) 1 1 [0.839]
-Total_time - 109.804 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 134.8 97.996 (1, 6, 10, 10, 1) 2 1 [134.8]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.796 1.306 (1, 6, 10, 10) 1 1 [1.796]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.96 0.698 (1, 1, 10, 10, 3) 1 1 [0.96]
+Total_time - 137.556 - - - - -
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.653 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 26.673 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 6386686bf6..ab39f2e12f 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -460,7 +460,8 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 45.7MB/s]
+ 66%|######5 | 2.25M/3.42M [00:00<00:00, 23.6MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 33.6MB/s]
/workspace/python/tvm/relay/frontend/pytorch_utils.py:47: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
return LooseVersion(torch_ver) > ver
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
@@ -586,7 +587,7 @@ via the host <cite>main.cc`</cite> or if a Zephyr emulated board is selected as
Torch top-1 id: 282, class name: tiger cat
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.838 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.740 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 d60a9d192a..4de64eff59 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -528,7 +528,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpww30hnfu/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp4ulcyl6c/images/random'
</pre></div>
</div>
</div>
@@ -588,8 +588,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [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/tmpww30hnfu/images/target contains 8144 images
-/tmp/tmpww30hnfu/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp4ulcyl6c/images/target contains 8144 images
+/tmp/tmp4ulcyl6c/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -701,13 +701,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 39s - loss: 0.2041 - accuracy: 0.9268 - val_loss: 0.1426 - val_accuracy: 0.9505 - 39s/epoch - 120ms/step
+328/328 - 41s - loss: 0.2110 - accuracy: 0.9261 - val_loss: 0.1376 - val_accuracy: 0.9566 - 41s/epoch - 126ms/step
Epoch 2/3
-328/328 - 35s - loss: 0.1003 - accuracy: 0.9645 - val_loss: 0.1111 - val_accuracy: 0.9619 - 35s/epoch - 105ms/step
+328/328 - 35s - loss: 0.0943 - accuracy: 0.9641 - val_loss: 0.1931 - val_accuracy: 0.9377 - 35s/epoch - 107ms/step
Epoch 3/3
-328/328 - 34s - loss: 0.0673 - accuracy: 0.9734 - val_loss: 0.1161 - val_accuracy: 0.9641 - 34s/epoch - 105ms/step
+328/328 - 35s - loss: 0.0695 - accuracy: 0.9748 - val_loss: 0.1634 - val_accuracy: 0.9434 - 35s/epoch - 106ms/step
-<keras.callbacks.History object at 0x7f09c81fc990>
+<keras.callbacks.History object at 0x7fc43f735f90>
</pre></div>
</div>
</div>
@@ -971,7 +971,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 31.196 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 36.848 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 ada6a66e98..0a999c1e9b 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:38.761</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>07:53.941</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -354,27 +354,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">5. Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:31.196</p></td>
+<td><p>04:36.848</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">6. Model Tuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>01:22.653</p></td>
+<td><p>01:26.673</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">4. microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:18.838</p></td>
+<td><p>01:22.740</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">3. microTVM Ahead-of-Time (AOT) Compilation</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:10.444</p></td>
+<td><p>00:11.015</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_custom_ide.html#sphx-glr-how-to-work-with-microtvm-micro-custom-ide-py"><span class="std std-ref">9. Bring microTVM to your own development environment</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_custom_ide.py</span></code>)</p></td>
-<td><p>00:08.081</p></td>
+<td><p>00:08.794</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">2. microTVM TFLite Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:07.548</p></td>
+<td><p>00:07.870</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">7. Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 4a5289c8a6..7c1fe414cb 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:36.757</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:39.468</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -354,19 +354,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.268</p></td>
+<td><p>00:34.455</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:02.880</p></td>
+<td><p>00:03.080</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>00:01.603</p></td>
+<td><p>00:01.926</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index dbe7959967..28148cd376 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -554,7 +554,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f074add9d40>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fc08d8645f0>
</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 8c5f78e092..e7016e588c 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -345,7 +345,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:08.294</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:09.340</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -354,35 +354,35 @@
</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>00:05.474</p></td>
+<td><p>00:06.372</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>00:01.294</p></td>
+<td><p>00:01.366</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>00:00.631</p></td>
+<td><p>00:00.664</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>00:00.614</p></td>
+<td><p>00:00.640</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>00:00.132</p></td>
+<td><p>00:00.139</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.065</p></td>
+<td><p>00:00.066</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.055</p></td>
+<td><p>00:00.061</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>00:00.030</p></td>
+<td><p>00:00.033</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/reference/api/doxygen/classtvm_1_1SEqualReducer-members.html b/docs/reference/api/doxygen/classtvm_1_1SEqualReducer-members.html
index 61211b0057..8b7044a82e 100644
--- a/docs/reference/api/doxygen/classtvm_1_1SEqualReducer-members.html
+++ b/docs/reference/api/doxygen/classtvm_1_1SEqualReducer-members.html
@@ -73,21 +73,22 @@ $(function() {
<tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">FreeVarEqualImpl</a>(const runtime::Object *lhs, const runtime::Object *rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a2c9d8f8cc9c98e544203874413b32b25">GetCurrentObjectPaths</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a74b0cfae81ee9911078700377a8ac80d">IsPathTracingEnabled</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#ab8192a058d6e7e19b39685be482a0bc2">operator()</a>(const double &lhs, const double &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a9e51ebf4da1133a20881550a93584bc2">operator()</a>(const int64_t &lhs, const int64_t &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#afa449f89cce1f8b97542f93872f3c86f">operator()</a>(const uint64_t &lhs, const uint64_t &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#afac9dee8ef58b7c7a0c12da33ea5a127">operator()</a>(const int &lhs, const int &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#abfb258ea4e73e86df459b577f959462f">operator()</a>(const bool &lhs, const bool &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a0af307366566580ec5809cf66f11dda2">operator()</a>(const std::string &lhs, const std::string &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#adb2b037903e6294de639f48ab5774902">operator()</a>(const DataType &lhs, const DataType &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a223371ab1879c2be58507790ada6300e">operator()</a>(const ENum &lhs, const ENum &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a4287b491de3193be1446ce74c2d3b90b">operator()</a>(const ObjectRef &lhs, const ObjectRef &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a6a381ad92eae02745a5c95c098fc38ec">operator()</a>(const ObjectRef &lhs, const ObjectRef &rhs, const ObjectPathPair &paths) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a9e7206f06f19162849a0c0a7f3258e7b">operator()</a>(const Array< T > &lhs, const Array< T > &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#af5d3b2a3d0a59a2f029f68157f917446">operator-></a>() const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a9d7dd06f0cb2ebf44a2e8938aae0ad7e">RecordMismatchPaths</a>(const ObjectPathPair &paths) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#abb85d3142af880fb96ae79423e5c382e">SEqualReducer</a>()=default</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a97eb296b45fee73c0ff6064c8eebdd7c">SEqualReducer</a>(Handler *handler, const PathTracingData *tracing_data, bool map_free_vars)</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">explicit</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#af39b835295a60e06d2a7b59f49df83a5">operator()</a>(const double &lhs, const double &rhs, Optional< ObjectPathPair > paths=NullOpt) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#add876af99fa9f27373ccf6394daf59bd">operator()</a>(const int64_t &lhs, const int64_t &rhs, Optional< ObjectPathPair > paths=NullOpt) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#aebfe8419c337476a330b1dfd5bc5ca7f">operator()</a>(const uint64_t &lhs, const uint64_t &rhs, Optional< ObjectPathPair > paths=NullOpt) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a87784e3639e005bb8cae8a4fa6afb4e8">operator()</a>(const int &lhs, const int &rhs, Optional< ObjectPathPair > paths=NullOpt) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a0ce5e074a6c684c88490a78632316599">operator()</a>(const bool &lhs, const bool &rhs, Optional< ObjectPathPair > paths=NullOpt) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a6d1faa66358e0de058e2bdbd4b49c12c">operator()</a>(const std::string &lhs, const std::string &rhs, Optional< ObjectPathPair > paths=NullOpt) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#ab9d11bbd982d13b0facb5acbe425544d">operator()</a>(const DataType &lhs, const DataType &rhs, Optional< ObjectPathPair > paths=NullOpt) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#ad17a9c210bd6bd40698e0fbe07a3d1a9">operator()</a>(const ENum &lhs, const ENum &rhs, Optional< ObjectPathPair > paths=NullOpt) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a9e2bb7f75e460b24a0feada7c991cff6">operator()</a>(const T &lhs, const T &rhs, const Callable &callable)</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a4287b491de3193be1446ce74c2d3b90b">operator()</a>(const ObjectRef &lhs, const ObjectRef &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a6a381ad92eae02745a5c95c098fc38ec">operator()</a>(const ObjectRef &lhs, const ObjectRef &rhs, const ObjectPathPair &paths) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a9e7206f06f19162849a0c0a7f3258e7b">operator()</a>(const Array< T > &lhs, const Array< T > &rhs) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#af5d3b2a3d0a59a2f029f68157f917446">operator-></a>() const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a9d7dd06f0cb2ebf44a2e8938aae0ad7e">RecordMismatchPaths</a>(const ObjectPathPair &paths) const</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#abb85d3142af880fb96ae79423e5c382e">SEqualReducer</a>()=default</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html#a97eb296b45fee73c0ff6064c8eebdd7c">SEqualReducer</a>(Handler *handler, const PathTracingData *tracing_data, bool map_free_vars)</td><td class="entry"><a class="el" href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">explicit</span></td></tr>
</table></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/classtvm_1_1SEqualReducer.html b/docs/reference/api/doxygen/classtvm_1_1SEqualReducer.html
index 8bec9c1a6c..3bb7e665fc 100644
--- a/docs/reference/api/doxygen/classtvm_1_1SEqualReducer.html
+++ b/docs/reference/api/doxygen/classtvm_1_1SEqualReducer.html
@@ -96,24 +96,27 @@ Public Member Functions</h2></td></tr>
<tr class="memitem:a97eb296b45fee73c0ff6064c8eebdd7c"><td class="memItemLeft" align="right" valign="top"> </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#a97eb296b45fee73c0ff6064c8eebdd7c">SEqualReducer</a> (<a class="el" href="classtvm_1_1SEqualReducer_1_1Handler.html">Handler</a> *handler, const PathTracingData *tracing_data, bool map_free_vars)</td></tr>
<tr class="memdesc:a97eb296b45fee73c0ff6064c8eebdd7c"><td class="mdescLeft"> </td><td class="mdescRight"><a class="el" href="classtvm_1_1Constructor.html" title="Managed reference to ConstructorNode. ">Constructor</a> with a specific handler. <a href="#a97eb296b45fee73c0ff6064c8eebdd7c">More...</a><br /></td></tr>
<tr class="separator:a97eb296b45fee73c0ff6064c8eebdd7c"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:ab8192a058d6e7e19b39685be482a0bc2"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#ab8192a058d6e7e19b39685be482a0bc2">operator()</a> (const double &lhs, const double &rhs) const</td></tr>
-<tr class="memdesc:ab8192a058d6e7e19b39685be482a0bc2"><td class="mdescLeft"> </td><td class="mdescRight">Reduce condition to comparison of two attribute values. <a href="#ab8192a058d6e7e19b39685be482a0bc2">More...</a><br /></td></tr>
-<tr class="separator:ab8192a058d6e7e19b39685be482a0bc2"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a9e51ebf4da1133a20881550a93584bc2"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#a9e51ebf4da1133a20881550a93584bc2">operator()</a> (const int64_t &lhs, const int64_t &rhs) const</td></tr>
-<tr class="separator:a9e51ebf4da1133a20881550a93584bc2"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:afa449f89cce1f8b97542f93872f3c86f"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#afa449f89cce1f8b97542f93872f3c86f">operator()</a> (const uint64_t &lhs, const uint64_t &rhs) const</td></tr>
-<tr class="separator:afa449f89cce1f8b97542f93872f3c86f"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:afac9dee8ef58b7c7a0c12da33ea5a127"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#afac9dee8ef58b7c7a0c12da33ea5a127">operator()</a> (const int &lhs, const int &rhs) const</td></tr>
-<tr class="separator:afac9dee8ef58b7c7a0c12da33ea5a127"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:abfb258ea4e73e86df459b577f959462f"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#abfb258ea4e73e86df459b577f959462f">operator()</a> (const bool &lhs, const bool &rhs) const</td></tr>
-<tr class="separator:abfb258ea4e73e86df459b577f959462f"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a0af307366566580ec5809cf66f11dda2"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#a0af307366566580ec5809cf66f11dda2">operator()</a> (const std::string &lhs, const std::string &rhs) const</td></tr>
-<tr class="separator:a0af307366566580ec5809cf66f11dda2"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:adb2b037903e6294de639f48ab5774902"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#adb2b037903e6294de639f48ab5774902">operator()</a> (const <a class="el" href="namespacetvm.html#a41918af1a1dc386388639a9d3ad06c5d">DataType</a> &lhs, const <a class="el" href="namespacetvm.html#a41918af1a1dc386388639a9d3ad06c5d">DataType</a> &rhs) const</td></tr>
-<tr class="separator:adb2b037903e6294de639f48ab5774902"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a223371ab1879c2be58507790ada6300e"><td class="memTemplParams" colspan="2">template<typename ENum , typename = typename std::enable_if<std::is_enum<ENum>::value>::type> </td></tr>
-<tr class="memitem:a223371ab1879c2be58507790ada6300e"><td class="memTemplItemLeft" align="right" valign="top">bool </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#a223371ab1879c2be58507790ada6300e">operator()</a> (const ENum &lhs, const ENum &rhs) const</td></tr>
-<tr class="separator:a223371ab1879c2be58507790ada6300e"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:af39b835295a60e06d2a7b59f49df83a5"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#af39b835295a60e06d2a7b59f49df83a5">operator()</a> (const double &lhs, const double &rhs, <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > paths=<a class="el" href="names [...]
+<tr class="memdesc:af39b835295a60e06d2a7b59f49df83a5"><td class="mdescLeft"> </td><td class="mdescRight">Reduce condition to comparison of two attribute values. <a href="#af39b835295a60e06d2a7b59f49df83a5">More...</a><br /></td></tr>
+<tr class="separator:af39b835295a60e06d2a7b59f49df83a5"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:add876af99fa9f27373ccf6394daf59bd"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#add876af99fa9f27373ccf6394daf59bd">operator()</a> (const int64_t &lhs, const int64_t &rhs, <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > paths=<a class="el" href="nam [...]
+<tr class="separator:add876af99fa9f27373ccf6394daf59bd"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:aebfe8419c337476a330b1dfd5bc5ca7f"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#aebfe8419c337476a330b1dfd5bc5ca7f">operator()</a> (const uint64_t &lhs, const uint64_t &rhs, <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > paths=<a class="el" href="n [...]
+<tr class="separator:aebfe8419c337476a330b1dfd5bc5ca7f"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a87784e3639e005bb8cae8a4fa6afb4e8"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#a87784e3639e005bb8cae8a4fa6afb4e8">operator()</a> (const int &lhs, const int &rhs, <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > paths=<a class="el" href="namespacetv [...]
+<tr class="separator:a87784e3639e005bb8cae8a4fa6afb4e8"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a0ce5e074a6c684c88490a78632316599"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#a0ce5e074a6c684c88490a78632316599">operator()</a> (const bool &lhs, const bool &rhs, <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > paths=<a class="el" href="namespace [...]
+<tr class="separator:a0ce5e074a6c684c88490a78632316599"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a6d1faa66358e0de058e2bdbd4b49c12c"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#a6d1faa66358e0de058e2bdbd4b49c12c">operator()</a> (const std::string &lhs, const std::string &rhs, <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > paths=<a class="el" h [...]
+<tr class="separator:a6d1faa66358e0de058e2bdbd4b49c12c"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ab9d11bbd982d13b0facb5acbe425544d"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#ab9d11bbd982d13b0facb5acbe425544d">operator()</a> (const <a class="el" href="namespacetvm.html#a41918af1a1dc386388639a9d3ad06c5d">DataType</a> &lhs, const <a class="el" href="namespacetvm.html#a41918af1a1dc386388639a9d3ad06c5d">DataType</a> &rhs, <a class="el" href="class [...]
+<tr class="separator:ab9d11bbd982d13b0facb5acbe425544d"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ad17a9c210bd6bd40698e0fbe07a3d1a9"><td class="memTemplParams" colspan="2">template<typename ENum , typename = typename std::enable_if<std::is_enum<ENum>::value>::type> </td></tr>
+<tr class="memitem:ad17a9c210bd6bd40698e0fbe07a3d1a9"><td class="memTemplItemLeft" align="right" valign="top">bool </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#ad17a9c210bd6bd40698e0fbe07a3d1a9">operator()</a> (const ENum &lhs, const ENum &rhs, <a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > paths=<a class="el" href= [...]
+<tr class="separator:ad17a9c210bd6bd40698e0fbe07a3d1a9"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a9e2bb7f75e460b24a0feada7c991cff6"><td class="memTemplParams" colspan="2">template<typename T , typename Callable , typename = std::enable_if_t< std::is_same_v<std::invoke_result_t<Callable, const ObjectPath&>, ObjectPath>>> </td></tr>
+<tr class="memitem:a9e2bb7f75e460b24a0feada7c991cff6"><td class="memTemplItemLeft" align="right" valign="top">bool </td><td class="memTemplItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#a9e2bb7f75e460b24a0feada7c991cff6">operator()</a> (const T &lhs, const T &rhs, const Callable &callable)</td></tr>
+<tr class="separator:a9e2bb7f75e460b24a0feada7c991cff6"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a4287b491de3193be1446ce74c2d3b90b"><td class="memItemLeft" align="right" valign="top">bool </td><td class="memItemRight" valign="bottom"><a class="el" href="classtvm_1_1SEqualReducer.html#a4287b491de3193be1446ce74c2d3b90b">operator()</a> (const <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> &lhs, const <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html">ObjectRef</a> &rhs) const</td></tr>
<tr class="memdesc:a4287b491de3193be1446ce74c2d3b90b"><td class="mdescLeft"> </td><td class="mdescRight">Reduce condition to comparison of two objects. <a href="#a4287b491de3193be1446ce74c2d3b90b">More...</a><br /></td></tr>
<tr class="separator:a4287b491de3193be1446ce74c2d3b90b"><td class="memSeparator" colspan="2"> </td></tr>
@@ -358,8 +361,8 @@ Public Member Functions</h2></td></tr>
</div>
</div>
-<a id="ab8192a058d6e7e19b39685be482a0bc2"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#ab8192a058d6e7e19b39685be482a0bc2">◆ </a></span>operator()() <span class="overload">[1/11]</span></h2>
+<a id="af39b835295a60e06d2a7b59f49df83a5"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#af39b835295a60e06d2a7b59f49df83a5">◆ </a></span>operator()() <span class="overload">[1/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -374,7 +377,13 @@ Public Member Functions</h2></td></tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">const double & </td>
- <td class="paramname"><em>rhs</em> </td>
+ <td class="paramname"><em>rhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > </td>
+ <td class="paramname"><em>paths</em> = <code><a class="el" href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">NullOpt</a></code> </td>
</tr>
<tr>
<td></td>
@@ -387,8 +396,9 @@ Public Member Functions</h2></td></tr>
<p>Reduce condition to comparison of two attribute values. </p>
<dl class="params"><dt>Parameters</dt><dd>
<table class="params">
- <tr><td class="paramname">lhs</td><td>The left operand. </td></tr>
- <tr><td class="paramname">rhs</td><td>The right operand. </td></tr>
+ <tr><td class="paramname">lhs</td><td>The left operand.</td></tr>
+ <tr><td class="paramname">rhs</td><td>The right operand.</td></tr>
+ <tr><td class="paramname">paths</td><td>The paths to the LHS and RHS operands. If unspecified, will attempt to identify the attribute's address within the most recent ObjectRef. In general, the paths only require explicit handling for computed parameters (e.g. <code>array.size()</code>)</td></tr>
</table>
</dd>
</dl>
@@ -396,8 +406,8 @@ Public Member Functions</h2></td></tr>
</div>
</div>
-<a id="a9e51ebf4da1133a20881550a93584bc2"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a9e51ebf4da1133a20881550a93584bc2">◆ </a></span>operator()() <span class="overload">[2/11]</span></h2>
+<a id="add876af99fa9f27373ccf6394daf59bd"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#add876af99fa9f27373ccf6394daf59bd">◆ </a></span>operator()() <span class="overload">[2/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -412,7 +422,13 @@ Public Member Functions</h2></td></tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">const int64_t & </td>
- <td class="paramname"><em>rhs</em> </td>
+ <td class="paramname"><em>rhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > </td>
+ <td class="paramname"><em>paths</em> = <code><a class="el" href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">NullOpt</a></code> </td>
</tr>
<tr>
<td></td>
@@ -424,8 +440,8 @@ Public Member Functions</h2></td></tr>
</div>
</div>
-<a id="afa449f89cce1f8b97542f93872f3c86f"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#afa449f89cce1f8b97542f93872f3c86f">◆ </a></span>operator()() <span class="overload">[3/11]</span></h2>
+<a id="aebfe8419c337476a330b1dfd5bc5ca7f"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#aebfe8419c337476a330b1dfd5bc5ca7f">◆ </a></span>operator()() <span class="overload">[3/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -440,7 +456,13 @@ Public Member Functions</h2></td></tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">const uint64_t & </td>
- <td class="paramname"><em>rhs</em> </td>
+ <td class="paramname"><em>rhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > </td>
+ <td class="paramname"><em>paths</em> = <code><a class="el" href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">NullOpt</a></code> </td>
</tr>
<tr>
<td></td>
@@ -452,8 +474,8 @@ Public Member Functions</h2></td></tr>
</div>
</div>
-<a id="afac9dee8ef58b7c7a0c12da33ea5a127"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#afac9dee8ef58b7c7a0c12da33ea5a127">◆ </a></span>operator()() <span class="overload">[4/11]</span></h2>
+<a id="a87784e3639e005bb8cae8a4fa6afb4e8"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a87784e3639e005bb8cae8a4fa6afb4e8">◆ </a></span>operator()() <span class="overload">[4/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -468,7 +490,13 @@ Public Member Functions</h2></td></tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">const int & </td>
- <td class="paramname"><em>rhs</em> </td>
+ <td class="paramname"><em>rhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > </td>
+ <td class="paramname"><em>paths</em> = <code><a class="el" href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">NullOpt</a></code> </td>
</tr>
<tr>
<td></td>
@@ -480,8 +508,8 @@ Public Member Functions</h2></td></tr>
</div>
</div>
-<a id="abfb258ea4e73e86df459b577f959462f"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#abfb258ea4e73e86df459b577f959462f">◆ </a></span>operator()() <span class="overload">[5/11]</span></h2>
+<a id="a0ce5e074a6c684c88490a78632316599"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a0ce5e074a6c684c88490a78632316599">◆ </a></span>operator()() <span class="overload">[5/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -496,7 +524,13 @@ Public Member Functions</h2></td></tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">const bool & </td>
- <td class="paramname"><em>rhs</em> </td>
+ <td class="paramname"><em>rhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > </td>
+ <td class="paramname"><em>paths</em> = <code><a class="el" href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">NullOpt</a></code> </td>
</tr>
<tr>
<td></td>
@@ -508,8 +542,8 @@ Public Member Functions</h2></td></tr>
</div>
</div>
-<a id="a0af307366566580ec5809cf66f11dda2"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a0af307366566580ec5809cf66f11dda2">◆ </a></span>operator()() <span class="overload">[6/11]</span></h2>
+<a id="a6d1faa66358e0de058e2bdbd4b49c12c"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a6d1faa66358e0de058e2bdbd4b49c12c">◆ </a></span>operator()() <span class="overload">[6/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -524,7 +558,13 @@ Public Member Functions</h2></td></tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">const std::string & </td>
- <td class="paramname"><em>rhs</em> </td>
+ <td class="paramname"><em>rhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > </td>
+ <td class="paramname"><em>paths</em> = <code><a class="el" href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">NullOpt</a></code> </td>
</tr>
<tr>
<td></td>
@@ -536,8 +576,8 @@ Public Member Functions</h2></td></tr>
</div>
</div>
-<a id="adb2b037903e6294de639f48ab5774902"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#adb2b037903e6294de639f48ab5774902">◆ </a></span>operator()() <span class="overload">[7/11]</span></h2>
+<a id="ab9d11bbd982d13b0facb5acbe425544d"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#ab9d11bbd982d13b0facb5acbe425544d">◆ </a></span>operator()() <span class="overload">[7/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -552,7 +592,13 @@ Public Member Functions</h2></td></tr>
<td class="paramkey"></td>
<td></td>
<td class="paramtype">const <a class="el" href="namespacetvm.html#a41918af1a1dc386388639a9d3ad06c5d">DataType</a> & </td>
- <td class="paramname"><em>rhs</em> </td>
+ <td class="paramname"><em>rhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > </td>
+ <td class="paramname"><em>paths</em> = <code><a class="el" href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">NullOpt</a></code> </td>
</tr>
<tr>
<td></td>
@@ -564,8 +610,8 @@ Public Member Functions</h2></td></tr>
</div>
</div>
-<a id="a223371ab1879c2be58507790ada6300e"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a223371ab1879c2be58507790ada6300e">◆ </a></span>operator()() <span class="overload">[8/11]</span></h2>
+<a id="ad17a9c210bd6bd40698e0fbe07a3d1a9"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#ad17a9c210bd6bd40698e0fbe07a3d1a9">◆ </a></span>operator()() <span class="overload">[8/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -585,7 +631,13 @@ template<typename ENum , typename = typename std::enable_if<std::is_enum&
<td class="paramkey"></td>
<td></td>
<td class="paramtype">const ENum & </td>
- <td class="paramname"><em>rhs</em> </td>
+ <td class="paramname"><em>rhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype"><a class="el" href="classtvm_1_1runtime_1_1Optional.html">Optional</a>< <a class="el" href="classtvm_1_1ObjectPathPair.html">ObjectPathPair</a> > </td>
+ <td class="paramname"><em>paths</em> = <code><a class="el" href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">NullOpt</a></code> </td>
</tr>
<tr>
<td></td>
@@ -600,10 +652,54 @@ template<typename ENum , typename = typename std::enable_if<std::is_enum&
</table>
</div><div class="memdoc">
+</div>
+</div>
+<a id="a9e2bb7f75e460b24a0feada7c991cff6"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a9e2bb7f75e460b24a0feada7c991cff6">◆ </a></span>operator()() <span class="overload">[9/12]</span></h2>
+
+<div class="memitem">
+<div class="memproto">
+<div class="memtemplate">
+template<typename T , typename Callable , typename = std::enable_if_t< std::is_same_v<std::invoke_result_t<Callable, const ObjectPath&>, ObjectPath>>> </div>
+<table class="mlabels">
+ <tr>
+ <td class="mlabels-left">
+ <table class="memname">
+ <tr>
+ <td class="memname">bool tvm::SEqualReducer::operator() </td>
+ <td>(</td>
+ <td class="paramtype">const T & </td>
+ <td class="paramname"><em>lhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">const T & </td>
+ <td class="paramname"><em>rhs</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">const Callable & </td>
+ <td class="paramname"><em>callable</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+ </td>
+ <td class="mlabels-right">
+<span class="mlabels"><span class="mlabel">inline</span></span> </td>
+ </tr>
+</table>
+</div><div class="memdoc">
+
</div>
</div>
<a id="a4287b491de3193be1446ce74c2d3b90b"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a4287b491de3193be1446ce74c2d3b90b">◆ </a></span>operator()() <span class="overload">[9/11]</span></h2>
+<h2 class="memtitle"><span class="permalink"><a href="#a4287b491de3193be1446ce74c2d3b90b">◆ </a></span>operator()() <span class="overload">[10/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -641,7 +737,7 @@ template<typename ENum , typename = typename std::enable_if<std::is_enum&
</div>
</div>
<a id="a6a381ad92eae02745a5c95c098fc38ec"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a6a381ad92eae02745a5c95c098fc38ec">◆ </a></span>operator()() <span class="overload">[10/11]</span></h2>
+<h2 class="memtitle"><span class="permalink"><a href="#a6a381ad92eae02745a5c95c098fc38ec">◆ </a></span>operator()() <span class="overload">[11/12]</span></h2>
<div class="memitem">
<div class="memproto">
@@ -696,7 +792,7 @@ template<typename ENum , typename = typename std::enable_if<std::is_enum&
</div>
</div>
<a id="a9e7206f06f19162849a0c0a7f3258e7b"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a9e7206f06f19162849a0c0a7f3258e7b">◆ </a></span>operator()() <span class="overload">[11/11]</span></h2>
+<h2 class="memtitle"><span class="permalink"><a href="#a9e7206f06f19162849a0c0a7f3258e7b">◆ </a></span>operator()() <span class="overload">[12/12]</span></h2>
<div class="memitem">
<div class="memproto">
diff --git a/docs/reference/api/doxygen/classtvm_1_1SEqualReducer__coll__graph.svg b/docs/reference/api/doxygen/classtvm_1_1SEqualReducer__coll__graph.svg
index 4e9dcb9893..aa12db097f 100644
--- a/docs/reference/api/doxygen/classtvm_1_1SEqualReducer__coll__graph.svg
+++ b/docs/reference/api/doxygen/classtvm_1_1SEqualReducer__coll__graph.svg
@@ -27,7 +27,7 @@
<text text-anchor="start" x="8" y="-40.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator()()</text>
<text text-anchor="start" x="8" y="-29.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator()()</text>
<text text-anchor="start" x="8" y="-18.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator()()</text>
-<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 9 more...</text>
+<text text-anchor="start" x="8" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 10 more...</text>
</g>
</g>
</svg>
diff --git a/docs/reference/api/doxygen/functions_func_o.html b/docs/reference/api/doxygen/functions_func_o.html
index cac4d8c5a3..1194deb106 100644
--- a/docs/reference/api/doxygen/functions_func_o.html
+++ b/docs/reference/api/doxygen/functions_func_o.html
@@ -193,7 +193,7 @@ $(function() {
, <a class="el" href="classtvm_1_1arith_1_1RewriteSimplifier.html#af91d307afc0c857751171a68d6d2b043">tvm::arith::RewriteSimplifier</a>
, <a class="el" href="structtvm_1_1auto__scheduler_1_1AttachMapNode_1_1IterKeyHash.html#a3754605e2a818ecbf7ef3ec891b7b6ce">tvm::auto_scheduler::AttachMapNode::IterKeyHash</a>
, <a class="el" href="classtvm_1_1BaseValueEqual.html#ab1d28212518d24cc1175b8b7ae2887d6">tvm::BaseValueEqual</a>
-, <a class="el" href="classtvm_1_1BaseValueHash.html#a68eb2b8b6501eced85bd52ac9a7e2ed6">tvm::BaseValueHash</a>
+, <a class="el" href="classtvm_1_1BaseValueHash.html#a25c40de503031b3dfa91003ccd014404">tvm::BaseValueHash</a>
, <a class="el" href="classtvm_1_1detail_1_1AttrDocVisitor.html#a1091752fc7d78b471b034877ad9344b3">tvm::detail::AttrDocVisitor</a>
, <a class="el" href="classtvm_1_1detail_1_1AttrExistVisitor.html#a345bb38b31b732a830eb9df3e16f6895">tvm::detail::AttrExistVisitor</a>
, <a class="el" href="classtvm_1_1detail_1_1AttrInitVisitor.html#af0856406dd74c88334291da4eff0543d">tvm::detail::AttrInitVisitor< FFind ></a>
@@ -219,7 +219,7 @@ $(function() {
, <a class="el" href="classtvm_1_1runtime_1_1TVMArgsSetter.html#a533c034c471f3c09341dcfbfcbb20d9a">tvm::runtime::TVMArgsSetter</a>
, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a987beda43b26ffc3665f1c448bf83e8c">tvm::runtime::TypedPackedFunc< R(Args...)></a>
, <a class="el" href="classtvm_1_1script_1_1printer_1_1IRDocsifierFunctor.html#a5fb47fd37745ce0057c2d5be1dc35c6e">tvm::script::printer::IRDocsifierFunctor< R, Args ></a>
-, <a class="el" href="classtvm_1_1SEqualReducer.html#ab8192a058d6e7e19b39685be482a0bc2">tvm::SEqualReducer</a>
+, <a class="el" href="classtvm_1_1SEqualReducer.html#af39b835295a60e06d2a7b59f49df83a5">tvm::SEqualReducer</a>
, <a class="el" href="classtvm_1_1SHashReducer.html#a259dd594f7eb56fef692f38668b0ecb1">tvm::SHashReducer</a>
, <a class="el" href="classtvm_1_1StructuralEqual.html#a1a8f9e17db557ecb536eaa41d3fd2465">tvm::StructuralEqual</a>
, <a class="el" href="classtvm_1_1StructuralHash.html#abd2a956462f7c67c74a4cd2e7c1db726">tvm::StructuralHash</a>
@@ -260,7 +260,7 @@ $(function() {
<li>operator++()
: <a class="el" href="classtvm_1_1runtime_1_1IterAdapter.html#a40f67dd792619d7d41ac45fc0f52a0c4">tvm::runtime::IterAdapter< Converter, TIter ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Map_1_1iterator.html#a8052ae36e24a4973c1a123c99cf5152c">tvm::runtime::Map< K, V, typename, typename >::iterator</a>
-, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a5230a8db9f60b62bc74d14ab8c3580ad">tvm::runtime::MapNode::iterator</a>
+, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#aa080c358ffab71cff472538a435eb615">tvm::runtime::MapNode::iterator</a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayIterator.html#a7e37edb0b1ba2d20e9d50af007d67bef">tvm::runtime::metadata::ArrayIterator< C, Ref ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ReverseIterAdapter.html#a362bd28f025d28551159e46c415309bd">tvm::runtime::ReverseIterAdapter< Converter, TIter ></a>
, <a class="el" href="classtvm_1_1support_1_1Span_1_1iterator__base.html#a526da770183e25f30104efb0ba4e62d5">tvm::support::Span< T, W >::iterator_base< W1 ></a>
@@ -271,7 +271,7 @@ $(function() {
<li>operator-()
: <a class="el" href="classtvm_1_1relay_1_1DFPattern.html#ad638d57cae9db9a1d4cd8831ab60a18b">tvm::relay::DFPattern</a>
, <a class="el" href="classtvm_1_1relay_1_1FeatureSet.html#ad0412921b6fe93a2f51b3c72c03c4095">tvm::relay::FeatureSet</a>
-, <a class="el" href="classtvm_1_1runtime_1_1IterAdapter.html#ab5671b2b9d56c2abcfb8d3f03cf6fd9e">tvm::runtime::IterAdapter< Converter, TIter ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1IterAdapter.html#a5bbe56d308014b49fec6374315f8d43a">tvm::runtime::IterAdapter< Converter, TIter ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ReverseIterAdapter.html#a67f728a692ed84a78a20a2095815f260">tvm::runtime::ReverseIterAdapter< Converter, TIter ></a>
</li>
<li>operator--()
@@ -293,7 +293,7 @@ $(function() {
, <a class="el" href="classtvm_1_1relay_1_1PatternWildcard.html#a106ab6e70f61976d2a7d5ca37ae26f51">tvm::relay::PatternWildcard</a>
, <a class="el" href="classtvm_1_1runtime_1_1Map_1_1iterator.html#a3779f858a014a0feea9d9e0c5d027d73">tvm::runtime::Map< K, V, typename, typename >::iterator</a>
, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#adf85d43ef116b85c8aa2a25599bc5584">tvm::runtime::MapNode::iterator</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Module.html#ab6d988e0c9c19eaec2970a0222cc4fc5">tvm::runtime::Module</a>
+, <a class="el" href="classtvm_1_1runtime_1_1Module.html#a87bcc010c62887a453d49d46854fa354">tvm::runtime::Module</a>
, <a class="el" href="classtvm_1_1runtime_1_1NDArray.html#ad57933f49a9fd51d7f996e1b16ffd2e0">tvm::runtime::NDArray</a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#a42a4f53709a0c071904c98e715ee7140">tvm::runtime::ObjectPtr< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#a3deeeac5827a88f375b8c6ae1039c219">tvm::runtime::ObjectRef</a>
@@ -303,12 +303,12 @@ $(function() {
, <a class="el" href="classtvm_1_1te_1_1IterVarAttr.html#aa1ef7fd178e47fd8165bb8fded785a28">tvm::te::IterVarAttr</a>
, <a class="el" href="classtvm_1_1te_1_1IterVarRelation.html#aa6a6afa23fa3c3a81b3778f2869b3455">tvm::te::IterVarRelation</a>
, <a class="el" href="classtvm_1_1te_1_1Operation.html#a133e5d2639c0c657131b53c0877cdd79">tvm::te::Operation</a>
-, <a class="el" href="classtvm_1_1te_1_1Schedule.html#a45d0647fe483156e98e76830db7c5130">tvm::te::Schedule</a>
+, <a class="el" href="classtvm_1_1te_1_1Schedule.html#aa30087792fd6d3b7372d56e7f3947c3f">tvm::te::Schedule</a>
, <a class="el" href="classtvm_1_1te_1_1Stage.html#a427ef4fef2edf15624be2c87bdad9505">tvm::te::Stage</a>
, <a class="el" href="classtvm_1_1tir_1_1Layout.html#a24d1414e53ab3bd153942bf5de5402e2">tvm::tir::Layout</a>
, <a class="el" href="classtvm_1_1tir_1_1SizeVar.html#ada44b624c1397c943ad9a0427378b048">tvm::tir::SizeVar</a>
, <a class="el" href="classtvm_1_1tir_1_1Var.html#a6a5db358f4fd7a9005a2d7a5f0fbe501">tvm::tir::Var</a>
-, <a class="el" href="classtvm_1_1transform_1_1PassContext.html#ab10baf6f7bcbd6e0e4b295399bc9f3a9">tvm::transform::PassContext</a>
+, <a class="el" href="classtvm_1_1transform_1_1PassContext.html#a2d1a6fffe70703812245b8d834da9a44">tvm::transform::PassContext</a>
, <a class="el" href="classtvm_1_1transform_1_1Sequential.html#a326b2bc7ce7710e22a91265b3aff37a0">tvm::transform::Sequential</a>
, <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#ab0177fd981b51149651e8912e6bf1b68">tvm::TypedEnvFunc< R(Args...)></a>
, <a class="el" href="classtvm_1_1TypeReporter.html#a64f4543a37a87db2fc57039a4ee6d3af">tvm::TypeReporter</a>
@@ -328,29 +328,29 @@ $(function() {
: <a class="el" href="classtvm_1_1arith_1_1Analyzer.html#a9dccc7d98b8b9465390e10436d3a9178">tvm::arith::Analyzer</a>
, <a class="el" href="classtvm_1_1Integer.html#ad538a2ae6f636b3ce38fb4162b1c2549">tvm::Integer</a>
, <a class="el" href="classtvm_1_1relay_1_1PatternWildcard.html#aef430b36a4be504969829f800e126245">tvm::relay::PatternWildcard</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Array.html#a5bc26222aa0257ece4c3a9d4d70fa1d8">tvm::runtime::Array< T, typename ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Array.html#a8f52fa8c97344586060ca735a3b91b39">tvm::runtime::Array< T, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1DataType.html#a3453c3a99d0bb6fcebf5a3629c8d37bb">tvm::runtime::DataType</a>
, <a class="el" href="classtvm_1_1runtime_1_1Map.html#a6b398835e5160e792634c8ee0783f284">tvm::runtime::Map< K, V, typename, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">tvm::runtime::Object</a>
-, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#afda3c65f41e83e1c87145a216f8c846d">tvm::runtime::ObjectPtr< T ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#af840ea1549dbe89d1680025c803e02e1">tvm::runtime::Optional< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#a4ea3532cb25b896b47b609c7db788bf8">tvm::runtime::ObjectPtr< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a377e159dbff53b8544a1b3337afc379d">tvm::runtime::Optional< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1String.html#aaf3615a763a98184d648c976565f6893">tvm::runtime::String</a>
-, <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#abf351bdd97209c8fb656b60abce7fccb">tvm::runtime::TVMRetValue</a>
-, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#aa590b3e712e06867805b41aaf17019ed">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+, <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#a400ab1f50cbbbc1ab24975bf32556d16">tvm::runtime::TVMRetValue</a>
+, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a8dd1fbae84cb9597c52977b0e8db64dc">tvm::runtime::TypedPackedFunc< R(Args...)></a>
, <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a69c12a9470f67ea26e53172f5c9220a1">tvm::runtime::vm::Instruction</a>
, <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#aab332907b9f98876f441f6403b801187">tvm::TypedEnvFunc< R(Args...)></a>
-, <a class="el" href="classtvm_1_1With.html#a58eb9398800f9889de022ddbb348921f">tvm::With< ContextType ></a>
+, <a class="el" href="classtvm_1_1With.html#a09cd315fd01e433ff9e5cf648d9bb948">tvm::With< ContextType ></a>
</li>
<li>operator==()
-: <a class="el" href="classtvm_1_1Integer.html#a5b9ad6d47c7c6df5a066d58f6ba65f8e">tvm::Integer</a>
+: <a class="el" href="classtvm_1_1Integer.html#ad2291d037ff36f5371f6381478b3eeaf">tvm::Integer</a>
, <a class="el" href="classtvm_1_1runtime_1_1DataType.html#a806810d87352f5c2bac1ad4e8d086a01">tvm::runtime::DataType</a>
, <a class="el" href="classtvm_1_1runtime_1_1IterAdapter.html#ac4066242008f1e60533099615a20fdbd">tvm::runtime::IterAdapter< Converter, TIter ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Map_1_1iterator.html#ade3c126684dcdc6ed432f3bb7eb62099">tvm::runtime::Map< K, V, typename, typename >::iterator</a>
, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a264c17028af85fe4619852f804e9464a">tvm::runtime::MapNode::iterator</a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayIterator.html#a6941bd0a5aa77acb1069e099e08455ed">tvm::runtime::metadata::ArrayIterator< C, Ref ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#ab849841f9277ad9015515ed591bf79d3">tvm::runtime::ObjectPtr< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#aeb6535554bf4a31d0e0bf80d5f23db29">tvm::runtime::ObjectPtr< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#affdf1b8cdb36e140de7b3ad7064e4617">tvm::runtime::ObjectRef</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a2e5b8e5065518ef40c70d5575edf8806">tvm::runtime::Optional< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#aba83dc01d0f82381c3505c20a6bb36b7">tvm::runtime::Optional< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1PackedFunc.html#a5c4ed23ffcb6a1874bd6eceb87b40b25">tvm::runtime::PackedFunc</a>
, <a class="el" href="classtvm_1_1runtime_1_1ReverseIterAdapter.html#ae71116873ea643de9f8ec1836cc116db">tvm::runtime::ReverseIterAdapter< Converter, TIter ></a>
, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a0e4a4d01d86eca79c5d9e1e90322c5cb">tvm::runtime::TypedPackedFunc< R(Args...)></a>
@@ -363,7 +363,7 @@ $(function() {
, <a class="el" href="classtvm_1_1AttrRegistryMapContainerMap.html#a713c3d1884423e3e67e3fdaef2566925">tvm::AttrRegistryMapContainerMap< KeyType ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ADT.html#a88cf389012aad0e129c84c056ae546fc">tvm::runtime::ADT</a>
, <a class="el" href="classtvm_1_1runtime_1_1Array.html#ac84683f61368eb10e26e72a0097cccd7">tvm::runtime::Array< T, typename ></a>
-, <a class="el" href="classtvm_1_1runtime_1_1InplaceArrayBase.html#a4b37b5fcd2285b818e8f623da8b326b2">tvm::runtime::InplaceArrayBase< ArrayType, ElemType ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1InplaceArrayBase.html#a45c91b04c230f7400727b1bc02a93f02">tvm::runtime::InplaceArrayBase< ArrayType, ElemType ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Map.html#a865a58097e473b532b1373bd15a1e91f">tvm::runtime::Map< K, V, typename, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayAccessor.html#a65fcb8067aa37421bb244573a07bb0b7">tvm::runtime::metadata::ArrayAccessor< C, Ref ></a>
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayAccessor_3_01const_01char_01_5_00_01_1_1tvm_1_1runtime_1_1String_01_4.html#ab5e946c37ae641eb9b541df79a54c3e5">tvm::runtime::metadata::ArrayAccessor< const char *, ::tvm::runtime::String ></a>
@@ -390,7 +390,7 @@ $(function() {
</li>
<li>Optional()
: <a class="el" href="classtvm_1_1relay_1_1DFPattern.html#aa573fa65bf9c4f0ba090225105233136">tvm::relay::DFPattern</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#aa07cc5bd536a18454ed737fb42b80be2">tvm::runtime::Optional< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#af684522b40606c8b5e0907fbd103291e">tvm::runtime::Optional< T ></a>
</li>
<li>Or()
: <a class="el" href="classtvm_1_1tir_1_1Or.html#ab0b68884ed84d03d3af7c95da2fcf81e">tvm::tir::Or</a>
diff --git a/docs/reference/api/doxygen/functions_o.html b/docs/reference/api/doxygen/functions_o.html
index d63b30b879..ca1fb34c9b 100644
--- a/docs/reference/api/doxygen/functions_o.html
+++ b/docs/reference/api/doxygen/functions_o.html
@@ -291,7 +291,7 @@ $(function() {
, <a class="el" href="classtvm_1_1runtime_1_1TVMArgsSetter.html#a533c034c471f3c09341dcfbfcbb20d9a">tvm::runtime::TVMArgsSetter</a>
, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a987beda43b26ffc3665f1c448bf83e8c">tvm::runtime::TypedPackedFunc< R(Args...)></a>
, <a class="el" href="classtvm_1_1script_1_1printer_1_1IRDocsifierFunctor.html#a5fb47fd37745ce0057c2d5be1dc35c6e">tvm::script::printer::IRDocsifierFunctor< R, Args ></a>
-, <a class="el" href="classtvm_1_1SEqualReducer.html#ab8192a058d6e7e19b39685be482a0bc2">tvm::SEqualReducer</a>
+, <a class="el" href="classtvm_1_1SEqualReducer.html#af39b835295a60e06d2a7b59f49df83a5">tvm::SEqualReducer</a>
, <a class="el" href="classtvm_1_1SHashReducer.html#a259dd594f7eb56fef692f38668b0ecb1">tvm::SHashReducer</a>
, <a class="el" href="classtvm_1_1StructuralEqual.html#a1a8f9e17db557ecb536eaa41d3fd2465">tvm::StructuralEqual</a>
, <a class="el" href="classtvm_1_1StructuralHash.html#abd2a956462f7c67c74a4cd2e7c1db726">tvm::StructuralHash</a>
@@ -350,7 +350,7 @@ $(function() {
<li>operator--()
: <a class="el" href="classtvm_1_1runtime_1_1IterAdapter.html#acb643cc554062422a4fd00bbfb3b0a6d">tvm::runtime::IterAdapter< Converter, TIter ></a>
, <a class="el" href="classtvm_1_1runtime_1_1MapNode_1_1iterator.html#a08393c19a1c8b1c4057a33832cd48662">tvm::runtime::MapNode::iterator</a>
-, <a class="el" href="classtvm_1_1runtime_1_1ReverseIterAdapter.html#a3a04e74706f1a844a7347d9073494f62">tvm::runtime::ReverseIterAdapter< Converter, TIter ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1ReverseIterAdapter.html#afa7ed1b09064bb3d6dea7ad886145346">tvm::runtime::ReverseIterAdapter< Converter, TIter ></a>
</li>
<li>operator-=()
: <a class="el" href="classtvm_1_1relay_1_1FeatureSet.html#ad90ce4d929774c0feb92c3eb56bea338">tvm::relay::FeatureSet</a>
@@ -405,7 +405,7 @@ $(function() {
: <a class="el" href="classtvm_1_1arith_1_1Analyzer.html#a9dccc7d98b8b9465390e10436d3a9178">tvm::arith::Analyzer</a>
, <a class="el" href="classtvm_1_1Integer.html#ad538a2ae6f636b3ce38fb4162b1c2549">tvm::Integer</a>
, <a class="el" href="classtvm_1_1relay_1_1PatternWildcard.html#aef430b36a4be504969829f800e126245">tvm::relay::PatternWildcard</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Array.html#a5bc26222aa0257ece4c3a9d4d70fa1d8">tvm::runtime::Array< T, typename ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Array.html#a8f52fa8c97344586060ca735a3b91b39">tvm::runtime::Array< T, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1DataType.html#a3453c3a99d0bb6fcebf5a3629c8d37bb">tvm::runtime::DataType</a>
, <a class="el" href="classtvm_1_1runtime_1_1Map.html#ac62909410a98a078ff01f688cdf70ffe">tvm::runtime::Map< K, V, typename, typename ></a>
, <a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">tvm::runtime::Object</a>
@@ -413,7 +413,7 @@ $(function() {
, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a98b43ed21bc060868ac03dab520a5da2">tvm::runtime::Optional< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1String.html#a3b3c8614af05adc454f47132e04552ed">tvm::runtime::String</a>
, <a class="el" href="classtvm_1_1runtime_1_1TVMRetValue.html#a4993d4b338c28096b56ed3d0d9ae5170">tvm::runtime::TVMRetValue</a>
-, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#aa590b3e712e06867805b41aaf17019ed">tvm::runtime::TypedPackedFunc< R(Args...)></a>
+, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a8dd1fbae84cb9597c52977b0e8db64dc">tvm::runtime::TypedPackedFunc< R(Args...)></a>
, <a class="el" href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a69c12a9470f67ea26e53172f5c9220a1">tvm::runtime::vm::Instruction</a>
, <a class="el" href="classtvm_1_1TypedEnvFunc_3_01R_07Args_8_8_8_08_4.html#aab332907b9f98876f441f6403b801187">tvm::TypedEnvFunc< R(Args...)></a>
, <a class="el" href="classtvm_1_1With.html#a58eb9398800f9889de022ddbb348921f">tvm::With< ContextType ></a>
@@ -427,7 +427,7 @@ $(function() {
, <a class="el" href="classtvm_1_1runtime_1_1metadata_1_1ArrayIterator.html#a6941bd0a5aa77acb1069e099e08455ed">tvm::runtime::metadata::ArrayIterator< C, Ref ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectPtr.html#ab849841f9277ad9015515ed591bf79d3">tvm::runtime::ObjectPtr< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1ObjectRef.html#affdf1b8cdb36e140de7b3ad7064e4617">tvm::runtime::ObjectRef</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#abb41934cee66ce6f25eba0f6de68ff1f">tvm::runtime::Optional< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#aba83dc01d0f82381c3505c20a6bb36b7">tvm::runtime::Optional< T ></a>
, <a class="el" href="classtvm_1_1runtime_1_1PackedFunc.html#a5c4ed23ffcb6a1874bd6eceb87b40b25">tvm::runtime::PackedFunc</a>
, <a class="el" href="classtvm_1_1runtime_1_1ReverseIterAdapter.html#ae71116873ea643de9f8ec1836cc116db">tvm::runtime::ReverseIterAdapter< Converter, TIter ></a>
, <a class="el" href="classtvm_1_1runtime_1_1TypedPackedFunc_3_01R_07Args_8_8_8_08_4.html#a0e4a4d01d86eca79c5d9e1e90322c5cb">tvm::runtime::TypedPackedFunc< R(Args...)></a>
@@ -449,7 +449,7 @@ $(function() {
, <a class="el" href="classtvm_1_1script_1_1printer_1_1ExprDoc.html#ae1f6796aeb37346a3962d70cf1c0a5b7">tvm::script::printer::ExprDoc</a>
, <a class="el" href="classtvm_1_1script_1_1printer_1_1ExprDocNode.html#ac353b9e318287f71827131a2c29a91e3">tvm::script::printer::ExprDocNode</a>
, <a class="el" href="classtvm_1_1support_1_1Span.html#ac9f8667c4b7baa4b2dba95d70f0245c0">tvm::support::Span< T, W ></a>
-, <a class="el" href="classtvm_1_1te_1_1Schedule.html#a3f63b27dcbddd06c550cc1a5a6562717">tvm::te::Schedule</a>
+, <a class="el" href="classtvm_1_1te_1_1Schedule.html#a2040189df3b89304a12acce3efff04a6">tvm::te::Schedule</a>
, <a class="el" href="classtvm_1_1te_1_1Tensor.html#a4cf42a49cf51e5aa8d33c32885a7129e">tvm::te::Tensor</a>
, <a class="el" href="classtvm_1_1te_1_1Tensor_1_1Slice.html#a1a00e3ec5f80973c337b0e7ab9c0974d">tvm::te::Tensor::Slice</a>
, <a class="el" href="classtvm_1_1tir_1_1Layout.html#ab80c1b1c7c763b5609cddb0fb613dc5c">tvm::tir::Layout</a>
@@ -481,7 +481,7 @@ $(function() {
</li>
<li>Optional()
: <a class="el" href="classtvm_1_1relay_1_1DFPattern.html#aa573fa65bf9c4f0ba090225105233136">tvm::relay::DFPattern</a>
-, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#a4474559794818ad1257b70e681929938">tvm::runtime::Optional< T ></a>
+, <a class="el" href="classtvm_1_1runtime_1_1Optional.html#ae7344a4b601b13152afff14a8dc52857">tvm::runtime::Optional< T ></a>
</li>
<li>optional_homogeneous_target
: <a class="el" href="classtvm_1_1CompilationConfigNode.html#ac29775462c7f70a3711221871fbd3453">tvm::CompilationConfigNode</a>
diff --git a/docs/reference/api/doxygen/ir_2expr_8h_source.html b/docs/reference/api/doxygen/ir_2expr_8h_source.html
index 02ef7a6aba..1109373895 100644
--- a/docs/reference/api/doxygen/ir_2expr_8h_source.html
+++ b/docs/reference/api/doxygen/ir_2expr_8h_source.html
@@ -83,7 +83,7 @@ $(function() {
<div class="ttc" id="string_8h_html"><div class="ttname"><a href="string_8h.html">string.h</a></div><div class="ttdoc">Runtime String container types. </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TVMPODValue___html"><div class="ttname"><a href="classtvm_1_1runtime_1_1TVMPODValue__.html">tvm::runtime::TVMPODValue_</a></div><div class="ttdoc">Internal base class to handle conversion to POD values. </div><div class="ttdef"><b>Definition:</b> packed_func.h:541</div></div>
<div class="ttc" id="classtvm_1_1RangeNode_html_a7903313f813a5cb7660a5448e2eeb2b4"><div class="ttname"><a href="classtvm_1_1RangeNode.html#a7903313f813a5cb7660a5448e2eeb2b4">tvm::RangeNode::SHashReduce</a></div><div class="ttdeci">void SHashReduce(SHashReducer hash_reduce) const</div><div class="ttdef"><b>Definition:</b> expr.h:703</div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
<div class="ttc" id="classtvm_1_1SEqualReducer_html"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></div><div class="ttdoc">A Reducer class to reduce the structural equality result of two objects. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:124</div></div>
<div class="ttc" id="classtvm_1_1BaseExprNode_html_a13d7d1f1e6f790951caf200cd59c3620"><div class="ttname"><a href="classtvm_1_1BaseExprNode.html#a13d7d1f1e6f790951caf200cd59c3620">tvm::BaseExprNode::_type_has_method_shash_reduce</a></div><div class="ttdeci">static constexpr const bool _type_has_method_shash_reduce</div><div class="ttdef"><b>Definition:</b> expr.h:59</div></div>
<div class="ttc" id="classtvm_1_1Integer_html_a2d3969d98441b5b2ee5d8a986a56c410"><div class="ttname"><a href="classtvm_1_1Integer.html#a2d3969d98441b5b2ee5d8a986a56c410">tvm::Integer::Integer</a></div><div class="ttdeci">Integer()</div><div class="ttdef"><b>Definition:</b> expr.h:624</div></div>
diff --git a/docs/reference/api/doxygen/ir_2type_8h_source.html b/docs/reference/api/doxygen/ir_2type_8h_source.html
index c853c739ee..e4665d15db 100644
--- a/docs/reference/api/doxygen/ir_2type_8h_source.html
+++ b/docs/reference/api/doxygen/ir_2type_8h_source.html
@@ -80,7 +80,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1TypeNode_html_a7b06d502a5162d51bb205691bbb95bb5"><div class="ttname"><a href="classtvm_1_1TypeNode.html#a7b06d502a5162d51bb205691bbb95bb5">tvm::TypeNode::span</a></div><div class="ttdeci">Span span</div><div class="ttdoc">Span that points to the original source code. Reserved debug information. </div><div class="ttdef"><b>Definition:</b> type.h:80</div></div>
<div class="ttc" id="classtvm_1_1PrimTypeNode_html_a3095121c58f824e258f2ac2f345ae7d1"><div class="ttname"><a href="classtvm_1_1PrimTypeNode.html#a3095121c58f824e258f2ac2f345ae7d1">tvm::PrimTypeNode::dtype</a></div><div class="ttdeci">runtime::DataType dtype</div><div class="ttdoc">The corresponding dtype field. </div><div class="ttdef"><b>Definition:</b> type.h:111</div></div>
<div class="ttc" id="classtvm_1_1TypeVarNode_html_a098a0b4e2ad1f3c8010a66bef2585ec4"><div class="ttname"><a href="classtvm_1_1TypeVarNode.html#a098a0b4e2ad1f3c8010a66bef2585ec4">tvm::TypeVarNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const TypeVarNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> type.h:264</div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
<div class="ttc" id="classtvm_1_1SEqualReducer_html"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></div><div class="ttdoc">A Reducer class to reduce the structural equality result of two objects. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:124</div></div>
<div class="ttc" id="classtvm_1_1TypeVarNode_html_a1ff00c9482ca9e0366e40237180189c7"><div class="ttname"><a href="classtvm_1_1TypeVarNode.html#a1ff00c9482ca9e0366e40237180189c7">tvm::TypeVarNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> type.h:258</div></div>
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
diff --git a/docs/reference/api/doxygen/relay_2base_8h_source.html b/docs/reference/api/doxygen/relay_2base_8h_source.html
index 6e309a8a09..46777e6a96 100644
--- a/docs/reference/api/doxygen/relay_2base_8h_source.html
+++ b/docs/reference/api/doxygen/relay_2base_8h_source.html
@@ -69,7 +69,7 @@ $(function() {
<a href="relay_2base_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more [...]
<div class="ttc" id="classtvm_1_1SHashReducer_html_a6cab7ab9b4adbab253001be6d3b4cdfe"><div class="ttname"><a href="classtvm_1_1SHashReducer.html#a6cab7ab9b4adbab253001be6d3b4cdfe">tvm::SHashReducer::FreeVarHashImpl</a></div><div class="ttdeci">void FreeVarHashImpl(const runtime::Object *var) const</div><div class="ttdoc">Implementation for hash for a free var. </div><div class="ttdef"><b>Definition:</b> structural_hash.h:193</div></div>
<div class="ttc" id="node_8h_html"><div class="ttname"><a href="node_8h.html">node.h</a></div><div class="ttdoc">Definitions and helper macros for IR/AST nodes. </div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
<div class="ttc" id="classtvm_1_1SEqualReducer_html"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></div><div class="ttdoc">A Reducer class to reduce the structural equality result of two objects. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:124</div></div>
<div class="ttc" id="classtvm_1_1relay_1_1IdNode_html"><div class="ttname"><a href="classtvm_1_1relay_1_1IdNode.html">tvm::relay::IdNode</a></div><div class="ttdoc">The unique identifier of variables. </div><div class="ttdef"><b>Definition:</b> base.h:89</div></div>
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
diff --git a/docs/reference/api/doxygen/search/all_10.js b/docs/reference/api/doxygen/search/all_10.js
index 95d4461e59..af384d7023 100644
--- a/docs/reference/api/doxygen/search/all_10.js
+++ b/docs/reference/api/doxygen/search/all_10.js
@@ -78,7 +78,7 @@ var searchData=
['operator_21_3d',['operator!=',['../classtvm_1_1Integer.html#a49869e0f187d66dcd00568d3e953fc04',1,'tvm::Integer::operator!=(int other) const'],['../classtvm_1_1Integer.html#a1e099442e256b242fe8e2e2a49c1dc33',1,'tvm::Integer::operator!=(Enum other) const'],['../classtvm_1_1runtime_1_1IterAdapter.html#a6e54667aa71ae41d33c22d6bd3973404',1,'tvm::runtime::IterAdapter::operator!=()'],['../classtvm_1_1runtime_1_1ReverseIterAdapter.html#a2a049030ff85513916a05924bf519d2c',1,'tvm::runtime::Reve [...]
['operator_25',['operator%',['../namespacetvm.html#ab25738e50b37cd07b2d171ca74ba9321',1,'tvm']]],
['operator_26_26',['operator&&',['../namespacetvm_1_1te.html#a45c2369417cfb6d8f20c400bcb1a693c',1,'tvm::te::operator&&(const Tensor::Slice &a, const T &b)'],['../namespacetvm_1_1te.html#a72b7fda8c6d5b169296d3d12522cb40f',1,'tvm::te::operator&&(const T &a, const Tensor::Slice &b)'],['../namespacetvm_1_1te.html#a8f10bf673f27ec755a0f284f3115c2ea',1,'tvm::te::operator&&(const Tensor::Slice &a, const Tensor::Slice &b)']]],
- ['operator_28_29',['operator()',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#add50f8cc72f7fbf50e456d31f045d24c',1,'tvm::arith::ConstIntBoundAnalyzer::operator()(const PrimExpr &expr) const'],['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#aa24f8d56b331e1b9c6ed315877c4e0a2',1,'tvm::arith::ConstIntBoundAnalyzer::operator()(const PrimExpr &expr, BoundMapType *bound)'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a57c3c62ebc821f5f01bc2b43f06488da',1,'tvm::arith::M [...]
+ ['operator_28_29',['operator()',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#add50f8cc72f7fbf50e456d31f045d24c',1,'tvm::arith::ConstIntBoundAnalyzer::operator()(const PrimExpr &expr) const'],['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#aa24f8d56b331e1b9c6ed315877c4e0a2',1,'tvm::arith::ConstIntBoundAnalyzer::operator()(const PrimExpr &expr, BoundMapType *bound)'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a57c3c62ebc821f5f01bc2b43f06488da',1,'tvm::arith::M [...]
['operator_2a',['operator*',['../classtvm_1_1relay_1_1DFPattern.html#a000e12a821910cb9bfb5c5df0b9f21ae',1,'tvm::relay::DFPattern::operator*()'],['../classtvm_1_1runtime_1_1IterAdapter.html#a4869a61f3e598fcbf8cdb3c14d66f859',1,'tvm::runtime::IterAdapter::operator*()'],['../classtvm_1_1runtime_1_1ReverseIterAdapter.html#a0b4fc047041f8e1cb3454ee89120444a',1,'tvm::runtime::ReverseIterAdapter::operator*()'],['../classtvm_1_1runtime_1_1MapNode_1_1iterator.html#ac09b2cd5327e5102ab373b482530f1 [...]
['operator_2a_3d',['operator*=',['../namespacetvm.html#a9233d7b436ae52ac070442ba19caed18',1,'tvm']]],
['operator_2b',['operator+',['../classtvm_1_1arith_1_1IntGroupBounds.html#a5de071b5c736097d25fa1a508b06f565',1,'tvm::arith::IntGroupBounds::operator+()'],['../classtvm_1_1arith_1_1IntConstraintsTransform.html#a0a1965c2707e06b47776e574a9597db9',1,'tvm::arith::IntConstraintsTransform::operator+()'],['../classtvm_1_1relay_1_1DFPattern.html#a9074ec635ca5c4ffe0fa7b6f7d7fe394',1,'tvm::relay::DFPattern::operator+()'],['../classtvm_1_1relay_1_1FeatureSet.html#ac2448ecf37a176ad612a9765927ed4fa' [...]
diff --git a/docs/reference/api/doxygen/search/functions_f.js b/docs/reference/api/doxygen/search/functions_f.js
index 68819509ad..06cb6cdfb4 100644
--- a/docs/reference/api/doxygen/search/functions_f.js
+++ b/docs/reference/api/doxygen/search/functions_f.js
@@ -39,7 +39,7 @@ var searchData=
['operator_21_3d',['operator!=',['../classtvm_1_1Integer.html#a49869e0f187d66dcd00568d3e953fc04',1,'tvm::Integer::operator!=(int other) const'],['../classtvm_1_1Integer.html#a1e099442e256b242fe8e2e2a49c1dc33',1,'tvm::Integer::operator!=(Enum other) const'],['../classtvm_1_1runtime_1_1IterAdapter.html#a6e54667aa71ae41d33c22d6bd3973404',1,'tvm::runtime::IterAdapter::operator!=()'],['../classtvm_1_1runtime_1_1ReverseIterAdapter.html#a2a049030ff85513916a05924bf519d2c',1,'tvm::runtime::Reve [...]
['operator_25',['operator%',['../namespacetvm.html#ab25738e50b37cd07b2d171ca74ba9321',1,'tvm']]],
['operator_26_26',['operator&&',['../namespacetvm_1_1te.html#a45c2369417cfb6d8f20c400bcb1a693c',1,'tvm::te::operator&&(const Tensor::Slice &a, const T &b)'],['../namespacetvm_1_1te.html#a72b7fda8c6d5b169296d3d12522cb40f',1,'tvm::te::operator&&(const T &a, const Tensor::Slice &b)'],['../namespacetvm_1_1te.html#a8f10bf673f27ec755a0f284f3115c2ea',1,'tvm::te::operator&&(const Tensor::Slice &a, const Tensor::Slice &b)']]],
- ['operator_28_29',['operator()',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#add50f8cc72f7fbf50e456d31f045d24c',1,'tvm::arith::ConstIntBoundAnalyzer::operator()(const PrimExpr &expr) const'],['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#aa24f8d56b331e1b9c6ed315877c4e0a2',1,'tvm::arith::ConstIntBoundAnalyzer::operator()(const PrimExpr &expr, BoundMapType *bound)'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a57c3c62ebc821f5f01bc2b43f06488da',1,'tvm::arith::M [...]
+ ['operator_28_29',['operator()',['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#add50f8cc72f7fbf50e456d31f045d24c',1,'tvm::arith::ConstIntBoundAnalyzer::operator()(const PrimExpr &expr) const'],['../classtvm_1_1arith_1_1ConstIntBoundAnalyzer.html#aa24f8d56b331e1b9c6ed315877c4e0a2',1,'tvm::arith::ConstIntBoundAnalyzer::operator()(const PrimExpr &expr, BoundMapType *bound)'],['../classtvm_1_1arith_1_1ModularSetAnalyzer.html#a57c3c62ebc821f5f01bc2b43f06488da',1,'tvm::arith::M [...]
['operator_2a',['operator*',['../classtvm_1_1relay_1_1DFPattern.html#a000e12a821910cb9bfb5c5df0b9f21ae',1,'tvm::relay::DFPattern::operator*()'],['../classtvm_1_1runtime_1_1IterAdapter.html#a4869a61f3e598fcbf8cdb3c14d66f859',1,'tvm::runtime::IterAdapter::operator*()'],['../classtvm_1_1runtime_1_1ReverseIterAdapter.html#a0b4fc047041f8e1cb3454ee89120444a',1,'tvm::runtime::ReverseIterAdapter::operator*()'],['../classtvm_1_1runtime_1_1MapNode_1_1iterator.html#ac09b2cd5327e5102ab373b482530f1 [...]
['operator_2a_3d',['operator*=',['../namespacetvm.html#a9233d7b436ae52ac070442ba19caed18',1,'tvm']]],
['operator_2b',['operator+',['../classtvm_1_1arith_1_1IntGroupBounds.html#a5de071b5c736097d25fa1a508b06f565',1,'tvm::arith::IntGroupBounds::operator+()'],['../classtvm_1_1arith_1_1IntConstraintsTransform.html#a0a1965c2707e06b47776e574a9597db9',1,'tvm::arith::IntConstraintsTransform::operator+()'],['../classtvm_1_1relay_1_1DFPattern.html#a9074ec635ca5c4ffe0fa7b6f7d7fe394',1,'tvm::relay::DFPattern::operator+()'],['../classtvm_1_1relay_1_1FeatureSet.html#ac2448ecf37a176ad612a9765927ed4fa' [...]
diff --git a/docs/reference/api/doxygen/structural__equal_8h_source.html b/docs/reference/api/doxygen/structural__equal_8h_source.html
index 91bff2b17e..7b354e8363 100644
--- a/docs/reference/api/doxygen/structural__equal_8h_source.html
+++ b/docs/reference/api/doxygen/structural__equal_8h_source.html
@@ -66,13 +66,13 @@ $(function() {
<div class="title">structural_equal.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="structural__equal_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * o [...]
+<a href="structural__equal_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * o [...]
<div class="ttc" id="classtvm_1_1SEqualReducer_1_1Handler_html_a3971c2653bf9bae74dd940cd80085aef"><div class="ttname"><a href="classtvm_1_1SEqualReducer_1_1Handler.html#a3971c2653bf9bae74dd940cd80085aef">tvm::SEqualReducer::Handler::PathTracingData</a></div><div class="ttdeci">SEqualReducer::PathTracingData PathTracingData</div><div class="ttdef"><b>Definition:</b> structural_equal.h:178</div></div>
<div class="ttc" id="classtvm_1_1BaseValueEqual_html_a47b854c8cb7ae0e4117c8587b1ca7d87"><div class="ttname"><a href="classtvm_1_1BaseValueEqual.html#a47b854c8cb7ae0e4117c8587b1ca7d87">tvm::BaseValueEqual::operator()</a></div><div class="ttdeci">bool operator()(const uint64_t &lhs, const uint64_t &rhs) const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:49</div></div>
<div class="ttc" id="classtvm_1_1BaseValueEqual_html_aa85342117cc040157ee0ca5dcf9a748e"><div class="ttname"><a href="classtvm_1_1BaseValueEqual.html#aa85342117cc040157ee0ca5dcf9a748e">tvm::BaseValueEqual::operator()</a></div><div class="ttdeci">bool operator()(const std::string &lhs, const std::string &rhs) const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:52</div></div>
<div class="ttc" id="classtvm_1_1ObjectPathPairNode_html"><div class="ttname"><a href="classtvm_1_1ObjectPathPairNode.html">tvm::ObjectPathPairNode</a></div><div class="ttdoc">Pair of ObjectPaths, one for each object being tested for structural equality. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:63</div></div>
<div class="ttc" id="classtvm_1_1BaseValueEqual_html_ab1d28212518d24cc1175b8b7ae2887d6"><div class="ttname"><a href="classtvm_1_1BaseValueEqual.html#ab1d28212518d24cc1175b8b7ae2887d6">tvm::BaseValueEqual::operator()</a></div><div class="ttdeci">bool operator()(const double &lhs, const double &rhs) const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:40</div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
<div class="ttc" id="classtvm_1_1BaseValueEqual_html_a77d0cce528fb92c5187e11d452b169f9"><div class="ttname"><a href="classtvm_1_1BaseValueEqual.html#a77d0cce528fb92c5187e11d452b169f9">tvm::BaseValueEqual::operator()</a></div><div class="ttdeci">bool operator()(const int &lhs, const int &rhs) const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:50</div></div>
<div class="ttc" id="classtvm_1_1SEqualReducer_html"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></div><div class="ttdoc">A Reducer class to reduce the structural equality result of two objects. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:124</div></div>
<div class="ttc" id="classtvm_1_1BaseValueEqual_html_a3b4e1128fc280531030b4d8b06c346eb"><div class="ttname"><a href="classtvm_1_1BaseValueEqual.html#a3b4e1128fc280531030b4d8b06c346eb">tvm::BaseValueEqual::operator()</a></div><div class="ttdeci">bool operator()(const DataType &lhs, const DataType &rhs) const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:53</div></div>
@@ -82,13 +82,14 @@ $(function() {
<div class="ttc" id="classtvm_1_1BaseValueEqual_html_a05031f178542fbfa16bf93637253a728"><div class="ttname"><a href="classtvm_1_1BaseValueEqual.html#a05031f178542fbfa16bf93637253a728">tvm::BaseValueEqual::operator()</a></div><div class="ttdeci">bool operator()(const ENum &lhs, const ENum &rhs) const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:55</div></div>
<div class="ttc" id="classtvm_1_1StructuralEqual_html"><div class="ttname"><a href="classtvm_1_1StructuralEqual.html">tvm::StructuralEqual</a></div><div class="ttdoc">Content-aware structural equality comparator for objects. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:103</div></div>
<div class="ttc" id="array_8h_html"><div class="ttname"><a href="array_8h.html">array.h</a></div><div class="ttdoc">Runtime Array container types. </div></div>
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_a9e2bb7f75e460b24a0feada7c991cff6"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#a9e2bb7f75e460b24a0feada7c991cff6">tvm::SEqualReducer::operator()</a></div><div class="ttdeci">bool operator()(const T &lhs, const T &rhs, const Callable &callable)</div><div class="ttdef"><b>Definition:</b> structural_equal.h:232</div></div>
<div class="ttc" id="classtvm_1_1BaseValueEqual_html_a65fe41787baaade1ee1d438f1e52ca19"><div class="ttname"><a href="classtvm_1_1BaseValueEqual.html#a65fe41787baaade1ee1d438f1e52ca19">tvm::BaseValueEqual::operator()</a></div><div class="ttdeci">bool operator()(const int64_t &lhs, const int64_t &rhs) const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:48</div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_a74b0cfae81ee9911078700377a8ac80d"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#a74b0cfae81ee9911078700377a8ac80d">tvm::SEqualReducer::IsPathTracingEnabled</a></div><div class="ttdeci">bool IsPathTracingEnabled() const</div><div class="ttdoc">Check if this reducer is tracing paths to the first mismatch. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:296</div></div>
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_a74b0cfae81ee9911078700377a8ac80d"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#a74b0cfae81ee9911078700377a8ac80d">tvm::SEqualReducer::IsPathTracingEnabled</a></div><div class="ttdeci">bool IsPathTracingEnabled() const</div><div class="ttdoc">Check if this reducer is tracing paths to the first mismatch. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:325</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_aed6387e67d18b9d5ad18f510fd600a25"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#aed6387e67d18b9d5ad18f510fd600a25">tvm::runtime::Array::size</a></div><div class="ttdeci">size_t size() const</div><div class="ttdef"><b>Definition:</b> array.h:420</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html">tvm::runtime::DataType</a></div><div class="ttdoc">Runtime primitive data type. </div><div class="ttdef"><b>Definition:</b> data_type.h:41</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html">tvm::runtime::Array</a></div><div class="ttdoc">Array, container representing a contiguous sequence of ObjectRefs. </div><div class="ttdef"><b>Definition:</b> array.h:289</div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_a223371ab1879c2be58507790ada6300e"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#a223371ab1879c2be58507790ada6300e">tvm::SEqualReducer::operator()</a></div><div class="ttdeci">bool operator()(const ENum &lhs, const ENum &rhs) const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:207</div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_a9e7206f06f19162849a0c0a7f3258e7b"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#a9e7206f06f19162849a0c0a7f3258e7b">tvm::SEqualReducer::operator()</a></div><div class="ttdeci">bool operator()(const Array< T > &lhs, const Array< T > &rhs) const</div><div class="ttdoc">Reduce condition to comparison of two arrays. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:262</div></div>
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_a9e7206f06f19162849a0c0a7f3258e7b"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#a9e7206f06f19162849a0c0a7f3258e7b">tvm::SEqualReducer::operator()</a></div><div class="ttdeci">bool operator()(const Array< T > &lhs, const Array< T > &rhs) const</div><div class="ttdoc">Reduce condition to comparison of two arrays. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:291</div></div>
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad17a9c210bd6bd40698e0fbe07a3d1a9"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad17a9c210bd6bd40698e0fbe07a3d1a9">tvm::SEqualReducer::operator()</a></div><div class="ttdeci">bool operator()(const ENum &lhs, const ENum &rhs, Optional< ObjectPathPair > paths=NullOpt) const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:221</div></div>
<div class="ttc" id="functor_8h_html"><div class="ttname"><a href="functor_8h.html">functor.h</a></div><div class="ttdoc">Defines the Functor data structures. </div></div>
<div class="ttc" id="object__path_8h_html"><div class="ttname"><a href="object__path_8h.html">object_path.h</a></div></div>
<div class="ttc" id="classtvm_1_1SEqualReducer_html_a97eb296b45fee73c0ff6064c8eebdd7c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#a97eb296b45fee73c0ff6064c8eebdd7c">tvm::SEqualReducer::SEqualReducer</a></div><div class="ttdeci">SEqualReducer(Handler *handler, const PathTracingData *tracing_data, bool map_free_vars)</div><div class="ttdoc">Constructor with a specific handler. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:189</div></div>
@@ -98,13 +99,14 @@ $(function() {
<div class="ttc" id="object_8h_html_a3aea9b3f65aeb9150c0fa7800e5573c6"><div class="ttname"><a href="object_8h.html#a3aea9b3f65aeb9150c0fa7800e5573c6">TVM_DECLARE_FINAL_OBJECT_INFO</a></div><div class="ttdeci">#define TVM_DECLARE_FINAL_OBJECT_INFO(TypeName, ParentType)</div><div class="ttdoc">helper macro to declare type information in a final class. </div><div class="ttdef"><b>Definition:</b> object.h:671</div></div>
<div class="ttc" id="data__type_8h_html"><div class="ttname"><a href="data__type_8h.html">data_type.h</a></div></div>
<div class="ttc" id="classtvm_1_1ObjectPathPairNode_html_ab0b0e402bc6722eb21829a8520d0031c"><div class="ttname"><a href="classtvm_1_1ObjectPathPairNode.html#ab0b0e402bc6722eb21829a8520d0031c">tvm::ObjectPathPairNode::rhs_path</a></div><div class="ttdeci">ObjectPath rhs_path</div><div class="ttdef"><b>Definition:</b> structural_equal.h:66</div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_a6a381ad92eae02745a5c95c098fc38ec"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#a6a381ad92eae02745a5c95c098fc38ec">tvm::SEqualReducer::operator()</a></div><div class="ttdeci">bool operator()(const ObjectRef &lhs, const ObjectRef &rhs, const ObjectPathPair &paths) const</div><div class="ttdoc">Reduce condition to comparison of two objects. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:237</div></div>
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_a6a381ad92eae02745a5c95c098fc38ec"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#a6a381ad92eae02745a5c95c098fc38ec">tvm::SEqualReducer::operator()</a></div><div class="ttdeci">bool operator()(const ObjectRef &lhs, const ObjectRef &rhs, const ObjectPathPair &paths) const</div><div class="ttdoc">Reduce condition to comparison of two objects. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:266</div></div>
<div class="ttc" id="classtvm_1_1ObjectPath_html"><div class="ttname"><a href="classtvm_1_1ObjectPath.html">tvm::ObjectPath</a></div><div class="ttdef"><b>Definition:</b> object_path.h:122</div></div>
<div class="ttc" id="classtvm_1_1BaseValueEqual_html"><div class="ttname"><a href="classtvm_1_1BaseValueEqual.html">tvm::BaseValueEqual</a></div><div class="ttdoc">Equality definition of base value class. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:38</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Optional_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Optional.html">tvm::runtime::Optional</a></div><div class="ttdoc">Optional container that to represent to a Nullable variant of T. </div><div class="ttdef"><b>Definition:</b> optional.h:51</div></div>
-<div class="ttc" id="classtvm_1_1SEqualHandlerDefault_html"><div class="ttname"><a href="classtvm_1_1SEqualHandlerDefault.html">tvm::SEqualHandlerDefault</a></div><div class="ttdoc">The default handler for equality testing. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:339</div></div>
+<div class="ttc" id="classtvm_1_1SEqualHandlerDefault_html"><div class="ttname"><a href="classtvm_1_1SEqualHandlerDefault.html">tvm::SEqualHandlerDefault</a></div><div class="ttdoc">The default handler for equality testing. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:370</div></div>
+<div class="ttc" id="namespacetvm_html_aae7034e3e41c18e7fb78ff32bfc6a318"><div class="ttname"><a href="namespacetvm.html#aae7034e3e41c18e7fb78ff32bfc6a318">tvm::NullOpt</a></div><div class="ttdeci">constexpr runtime::NullOptType NullOpt</div><div class="ttdef"><b>Definition:</b> optional.h:160</div></div>
<div class="ttc" id="object_8h_html_a782d0de62fbf75736e29c1e79c22c7f1"><div class="ttname"><a href="object_8h.html#a782d0de62fbf75736e29c1e79c22c7f1">TVM_DEFINE_NOTNULLABLE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_NOTNULLABLE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:728</div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_af5d3b2a3d0a59a2f029f68157f917446"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#af5d3b2a3d0a59a2f029f68157f917446">tvm::SEqualReducer::operator-></a></div><div class="ttdeci">Handler * operator->() const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:293</div></div>
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_af5d3b2a3d0a59a2f029f68157f917446"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#af5d3b2a3d0a59a2f029f68157f917446">tvm::SEqualReducer::operator-></a></div><div class="ttdeci">Handler * operator->() const</div><div class="ttdef"><b>Definition:</b> structural_equal.h:322</div></div>
</div><!-- fragment --></div><!-- contents -->
<!-- start footer part -->
<hr class="footer"/><address class="footer"><small>
diff --git a/docs/reference/api/doxygen/var_8h_source.html b/docs/reference/api/doxygen/var_8h_source.html
index 25020084c2..8540b768a7 100644
--- a/docs/reference/api/doxygen/var_8h_source.html
+++ b/docs/reference/api/doxygen/var_8h_source.html
@@ -73,7 +73,7 @@ $(function() {
<div class="ttc" id="node_8h_html"><div class="ttname"><a href="node_8h.html">node.h</a></div><div class="ttdoc">Definitions and helper macros for IR/AST nodes. </div></div>
<div class="ttc" id="classtvm_1_1tir_1_1VarNode_html_a629882d57604a710116f12976b40a043"><div class="ttname"><a href="classtvm_1_1tir_1_1VarNode.html#a629882d57604a710116f12976b40a043">tvm::tir::VarNode::TVM_DECLARE_BASE_OBJECT_INFO</a></div><div class="ttdeci">TVM_DECLARE_BASE_OBJECT_INFO(VarNode, PrimExprNode)</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1VarNode_html_ad9481f1386e2b002617a7ef93af13019"><div class="ttname"><a href="classtvm_1_1tir_1_1VarNode.html#ad9481f1386e2b002617a7ef93af13019">tvm::tir::VarNode::_type_child_slots</a></div><div class="ttdeci">static constexpr const uint32_t _type_child_slots</div><div class="ttdef"><b>Definition:</b> var.h:83</div></div>
-<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
+<div class="ttc" id="classtvm_1_1SEqualReducer_html_ad9c0e2985eb9d82eecc67ea0f008154c"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html#ad9c0e2985eb9d82eecc67ea0f008154c">tvm::SEqualReducer::FreeVarEqualImpl</a></div><div class="ttdeci">bool FreeVarEqualImpl(const runtime::Object *lhs, const runtime::Object *rhs) const</div><div class="ttdoc">Implementation for equality rule of var type objects(e.g. TypeVar, tir::Var). </div><div class="ttdef"><b>Definition:</b> structural_equ [...]
<div class="ttc" id="classtvm_1_1SEqualReducer_html"><div class="ttname"><a href="classtvm_1_1SEqualReducer.html">tvm::SEqualReducer</a></div><div class="ttdoc">A Reducer class to reduce the structural equality result of two objects. </div><div class="ttdef"><b>Definition:</b> structural_equal.h:124</div></div>
<div class="ttc" id="ir_2expr_8h_html"><div class="ttname"><a href="ir_2expr_8h.html">expr.h</a></div><div class="ttdoc">Base expr nodes in TVM. </div></div>
<div class="ttc" id="classtvm_1_1BaseExprNode_html_a13d7d1f1e6f790951caf200cd59c3620"><div class="ttname"><a href="classtvm_1_1BaseExprNode.html#a13d7d1f1e6f790951caf200cd59c3620">tvm::BaseExprNode::_type_has_method_shash_reduce</a></div><div class="ttdeci">static constexpr const bool _type_has_method_shash_reduce</div><div class="ttdef"><b>Definition:</b> expr.h:59</div></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index b06207cbc4..c1c7879ef7 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1621,7 +1621,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1905,7 +1905,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index a084552e59..398ae905c2 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/5239ec05e/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L45">rpc_server.ts:45</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L44">rpc_server.ts:44</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L65">rpc_server.ts:65</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L51">rpc_server.ts:51</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L59">rpc_server.ts:59</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index ef10a33aa2..b449dc8803 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/5239ec05e/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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 59959e661b..6b377f2ec6 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/5239ec05e/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L357">runtime.ts:357</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L357">runtime.ts:357</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L359">runtime.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L359">runtime.ts:359</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L376">runtime.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L376">runtime.ts:376</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L367">runtime.ts:367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L367">runtime.ts:367</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index f80fc116cf..2d3ba0adec 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/5239ec05e/web/src/runtime.ts#L299">runtime.ts:299</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L299">runtime.ts:299</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L320">runtime.ts:320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L320">runtime.ts:320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L327">runtime.ts:327</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L327">runtime.ts:327</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index dda8e9c186..94b77237a7 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/5239ec05e/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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 2b472af899..324eff2cbd 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/5239ec05e/web/src/runtime.ts#L50">runtime.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L50">runtime.ts:50</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L48">runtime.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L48">runtime.ts:48</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L77">runtime.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L77">runtime.ts:77</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L67">runtime.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L67">runtime.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L85">runtime.ts:85</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L85">runtime.ts:85</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L96">runtime.ts:96</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L96">runtime.ts:96</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L73">runtime.ts:73</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L73">runtime.ts:73</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 32f27830c9..73adb67d2e 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -161,7 +161,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L844">runtime.ts:844</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L844">runtime.ts:844</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L834">runtime.ts:834</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L834">runtime.ts:834</a></li>
</ul>
</aside>
</section>
@@ -234,7 +234,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L833">runtime.ts:833</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L833">runtime.ts:833</a></li>
</ul>
</aside>
</section>
@@ -251,7 +251,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L973">runtime.ts:973</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L973">runtime.ts:973</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -296,7 +296,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -318,7 +318,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L901">runtime.ts:901</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L901">runtime.ts:901</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -381,7 +381,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1215">runtime.ts:1215</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -412,7 +412,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1000">runtime.ts:1000</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -453,7 +453,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1207">runtime.ts:1207</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -491,7 +491,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L922">runtime.ts:922</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L922">runtime.ts:922</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -508,7 +508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1235">runtime.ts:1235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -552,7 +552,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L943">runtime.ts:943</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L943">runtime.ts:943</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -577,7 +577,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1088">runtime.ts:1088</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -609,7 +609,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1363">runtime.ts:1363</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -640,7 +640,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1123">runtime.ts:1123</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -672,7 +672,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1016">runtime.ts:1016</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -695,7 +695,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1281">runtime.ts:1281</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -729,7 +729,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L986">runtime.ts:986</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L986">runtime.ts:986</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -769,7 +769,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1341">runtime.ts:1341</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -817,7 +817,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1055">runtime.ts:1055</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -857,7 +857,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1320">runtime.ts:1320</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -900,7 +900,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1197">runtime.ts:1197</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -938,7 +938,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1491">runtime.ts:1491</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1009">runtime.ts:1009</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1014,7 +1014,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1151">runtime.ts:1151</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1046,7 +1046,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1078,7 +1078,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1292">runtime.ts:1292</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1110,7 +1110,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L1223">runtime.ts:1223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1141,7 +1141,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L957">runtime.ts:957</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L957">runtime.ts:957</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 35542536a9..1e3351d541 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/5239ec05e/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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 b6cde24f20..ba9dacd6f4 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L614">runtime.ts:614</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L614">runtime.ts:614</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L626">runtime.ts:626</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L626">runtime.ts:626</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -186,7 +186,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L653">runtime.ts:653</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L653">runtime.ts:653</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L641">runtime.ts:641</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L641">runtime.ts:641</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L687">runtime.ts:687</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L687">runtime.ts:687</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index d35a1195a9..5d0ee779f3 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/5239ec05e/web/src/runtime.ts#L401">runtime.ts:401</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L401">runtime.ts:401</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L394">runtime.ts:394</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L394">runtime.ts:394</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L390">runtime.ts:390</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L390">runtime.ts:390</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L388">runtime.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L388">runtime.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L392">runtime.ts:392</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L392">runtime.ts:392</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -225,7 +225,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L480">runtime.ts:480</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L480">runtime.ts:480</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -258,7 +258,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L524">runtime.ts:524</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L524">runtime.ts:524</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -290,7 +290,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L465">runtime.ts:465</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L465">runtime.ts:465</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -307,7 +307,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L458">runtime.ts:458</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L458">runtime.ts:458</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -339,7 +339,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L584">runtime.ts:584</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L584">runtime.ts:584</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -363,7 +363,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L553">runtime.ts:553</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L553">runtime.ts:553</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 01fdd95962..c87e9a9cac 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -117,7 +117,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L255">runtime.ts:255</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L255">runtime.ts:255</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -163,7 +163,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L264">runtime.ts:264</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L264">runtime.ts:264</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index f18ede3477..876139d150 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/5239ec05e/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L95">rpc_server.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L84">rpc_server.ts:84</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L83">rpc_server.ts:83</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/runtimecontext.html b/docs/reference/api/typedoc/classes/runtimecontext.html
index 8aa7d4e1fb..2defc579a3 100644
--- a/docs/reference/api/typedoc/classes/runtimecontext.html
+++ b/docs/reference/api/typedoc/classes/runtimecontext.html
@@ -132,7 +132,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L148">runtime.ts:148</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L148">runtime.ts:148</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Item<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
</section>
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Get<wbr>Size<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L144">runtime.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L144">runtime.ts:144</a></li>
</ul>
</aside>
</section>
@@ -192,7 +192,7 @@
<div class="tsd-signature tsd-kind-icon">array<wbr>Make<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
</section>
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Sys<wbr>Lib<span class="tsd-signature-symbol">:</span> <a href="../index.html#packedfunc" class="tsd-signature-type">PackedFunc</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L146">runtime.ts:146</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L146">runtime.ts:146</a></li>
</ul>
</aside>
</section>
@@ -219,7 +219,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -263,7 +263,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L163">runtime.ts:163</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L163">runtime.ts:163</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -280,7 +280,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L208">runtime.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L208">runtime.ts:208</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
@@ -309,7 +309,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -326,7 +326,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L167">runtime.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L167">runtime.ts:167</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -343,7 +343,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<h4 class="tsd-type-parameters-title">Type parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 5b64bda445..2fe9acd291 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/5239ec05e/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L235">runtime.ts:235</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L235">runtime.ts:235</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L233">runtime.ts:233</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L233">runtime.ts:233</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmarray.html b/docs/reference/api/typedoc/classes/tvmarray.html
index 81850354bf..0b1a349ec6 100644
--- a/docs/reference/api/typedoc/classes/tvmarray.html
+++ b/docs/reference/api/typedoc/classes/tvmarray.html
@@ -133,7 +133,7 @@
<aside class="tsd-sources">
<p>Overrides <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#constructor">constructor</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L784">runtime.ts:784</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L784">runtime.ts:784</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -162,7 +162,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#ctx">ctx</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#dispose">dispose</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -197,7 +197,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L804">runtime.ts:804</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L804">runtime.ts:804</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -230,7 +230,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#gethandle">getHandle</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L796">runtime.ts:796</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L796">runtime.ts:796</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -283,7 +283,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typeindex">typeIndex</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -306,7 +306,7 @@
<aside class="tsd-sources">
<p>Inherited from <a href="tvmobject.html">TVMObject</a>.<a href="tvmobject.html#typekey">typeKey</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/tvmobject.html b/docs/reference/api/typedoc/classes/tvmobject.html
index fef2780eb9..80eede36a0 100644
--- a/docs/reference/api/typedoc/classes/tvmobject.html
+++ b/docs/reference/api/typedoc/classes/tvmobject.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">ctx<span class="tsd-signature-symbol">:</span> <a href="runtimecontext.html" class="tsd-signature-type">RuntimeContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L703">runtime.ts:703</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L703">runtime.ts:703</a></li>
</ul>
</aside>
</section>
@@ -175,7 +175,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L715">runtime.ts:715</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L715">runtime.ts:715</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -192,7 +192,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L730">runtime.ts:730</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L730">runtime.ts:730</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L738">runtime.ts:738</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L738">runtime.ts:738</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -246,7 +246,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L758">runtime.ts:758</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L758">runtime.ts:758</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 42c595b9a4..300d3204b1 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/5239ec05e/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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/5239ec05e/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/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 43c66c464b..97d271956b 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/5239ec05e/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L242">ctypes.ts:242</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L238">ctypes.ts:238</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L236">ctypes.ts:236</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L240">ctypes.ts:240</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L248">ctypes.ts:248</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L243">ctypes.ts:243</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L241">ctypes.ts:241</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L245">ctypes.ts:245</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L249">ctypes.ts:249</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L244">ctypes.ts:244</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L250">ctypes.ts:250</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L239">ctypes.ts:239</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L246">ctypes.ts:246</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L247">ctypes.ts:247</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L237">ctypes.ts:237</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index a1f00e6d77..bc2f303062 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/5239ec05e/web/src/runtime.ts#L812">runtime.ts:812</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L812">runtime.ts:812</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L811">runtime.ts:811</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L811">runtime.ts:811</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index c94e883196..38519a00f5 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/5239ec05e/web/src/runtime.ts#L339">runtime.ts:339</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L339">runtime.ts:339</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L337">runtime.ts:337</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L337">runtime.ts:337</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L340">runtime.ts:340</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L340">runtime.ts:340</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L338">runtime.ts:338</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L338">runtime.ts:338</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 2d93692df9..955e5a684a 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/5239ec05e/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L34">rpc_server.ts:34</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L33">rpc_server.ts:33</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 19ca44e73f..fadfb08330 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/5239ec05e/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L229">ctypes.ts:229</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 5c4bbef183..5d075c9f85 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -182,7 +182,7 @@
<div class="tsd-signature tsd-kind-icon">FObject<wbr>Constructor<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, lib<span class="tsd-signature-symbol">: </span><a href="classes/ffilibrary.html" class="tsd-signature-type">FFILibrary</a>, ctx<span class="tsd-signature-symbol">: </span><a href="classes/runtimecontext.html" class="t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/runtime.ts#L778">runtime.ts:778</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/runtime.ts#L778">runtime.ts:778</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L113">ctypes.ts:113</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -288,7 +288,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L129">ctypes.ts:129</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L145">ctypes.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -376,7 +376,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L137">ctypes.ts:137</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -420,7 +420,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L122">ctypes.ts:122</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -456,7 +456,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L161">ctypes.ts:161</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -508,7 +508,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L78">ctypes.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -556,7 +556,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L84">ctypes.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -595,7 +595,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L68">ctypes.ts:68</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -651,7 +651,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L58">ctypes.ts:58</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -687,7 +687,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5239ec05e/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/af39b3441/web/src/ctypes.ts#L101">ctypes.ts:101</a></li>
</ul>
</aside>
... 1284 lines suppressed ...