You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2023/01/18 06:50:59 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@6c5be6fbd062a5cd431f09a1d87ac614cee73a39)
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 fdf7c51ca9 deploying docs (apache/tvm@6c5be6fbd062a5cd431f09a1d87ac614cee73a39)
fdf7c51ca9 is described below
commit fdf7c51ca9fac8fd1b5a9c7fe9d4efa53403b2eb
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Jan 18 06:50:53 2023 +0000
deploying docs (apache/tvm@6c5be6fbd062a5cd431f09a1d87ac614cee73a39)
---
docs/_images/sphx_glr_micro_train_001.png | Bin 314727 -> 324292 bytes
docs/_images/sphx_glr_micro_train_thumb.png | Bin 23008 -> 23851 bytes
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_keras.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_adreno.rst.txt | 7 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 20 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1406 ++++++++++++--------
.../tune_network_cuda.rst.txt | 4 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 2 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 10 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 95 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/micro_pytorch.rst.txt | 4 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 18 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 6 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 59 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_keras.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 14 +-
docs/how_to/compile_models/from_pytorch.html | 8 +-
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 | 3 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 37 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 38 +-
docs/how_to/deploy_models/sg_execution_times.html | 20 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1406 ++++++++++++--------
.../tune_with_autoscheduler/tune_network_cuda.html | 4 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 2 +-
.../tune_with_autotvm/sg_execution_times.html | 10 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 95 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_pytorch.html | 4 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 10 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 7 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 271 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
129 files changed, 2690 insertions(+), 1936 deletions(-)
diff --git a/docs/_images/sphx_glr_micro_train_001.png b/docs/_images/sphx_glr_micro_train_001.png
index 44d42e7073..fd04aec899 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 979e8de9bd..176d23232e 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 cdbe53d4da..21c072813d 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 16.087 seconds)
+ **Total running time of the script:** ( 1 minutes 14.880 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_keras.rst.txt b/docs/_sources/how_to/compile_models/from_keras.rst.txt
index 91bdc62360..0a0d472cfc 100644
--- a/docs/_sources/how_to/compile_models/from_keras.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_keras.rst.txt
@@ -232,7 +232,7 @@ Look up prediction top 1 index in 1000 class synset.
.. code-block:: none
Relay top-1 id: 285, class name: Egyptian cat
-
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 1s/step
+
1/1 [==============================] - ETA: 0s
1/1 [==============================] - 1s 880ms/step
Keras top-1 id: 285, class name: Egyptian cat
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index d09f184944..e25bdd0c81 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.zip39cab67a-948c-410c-b02a-9c120b33651c from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip362a85cc-5fe7-4587-9c52-f98a850c7209 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 dbdf1d5e58..f546bb71cf 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -121,7 +121,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 40.0MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 49.8MB/s]
47%|####6 | 19.5M/41.5M [00:00<00:00, 23.5MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 25.6MB/s]
77%|#######7 | 32.0M/41.5M [00:01<00:00, 34.3MB/s]
96%|#########6| 40.0M/41.5M [00:01<00:00, 43.1MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 37.4MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 44.4MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 53.6MB/s]
54%|#####3 | 22.3M/41.5M [00:00<00:00, 54.6MB/s]
67%|######6 | 27.7M/41.5M [00:00<00:00, 52.9MB/s]
82%|########2 | 34.1M/41.5M [00:00<00:00, 55.9MB/s]
96%|#########6| 40.0M/41.5M [00:00<00:00, 55.6MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 54.8MB/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 b6cfcdb214..0db8af73f5 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]
34%|###3 | 15.0M/44.7M [00:00<00:00, 157MB/s]
67%|######7 | 30.0M/44.7M [00:00<00:00, 117MB/s]
93%|#########3| 41.7M/44.7M [00:00<00:00, 110MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 114MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
30%|### | 13.6M/44.7M [00:00<00:00, 142MB/s]
65%|######4 | 28.9M/44.7M [00:00<00:00, 153MB/s]
97%|#########7| 43.4M/44.7M [00:00<00:00, 118MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 119MB/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 9bc8f7fb82..560ec2a99f 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -424,7 +424,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.758 seconds)
+ **Total running time of the script:** ( 1 minutes 17.877 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 063b0920ea..aa4a6bff6c 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
=================
-**06:21.595** total execution time for **how_to_compile_models** files:
+**06:07.783** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:21.758 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:17.877 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:16.087 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:14.880 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:52.066 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:50.409 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:36.680 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:33.733 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:30.902 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:29.568 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:30.273 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:29.300 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.591 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.765 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:24.772 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:23.543 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:19.853 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:19.171 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.615 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.536 | 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 1fafe232ea..1d71e11f24 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_adreno.rst.txt
@@ -727,18 +727,13 @@ 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)
- 3346.9771 3346.6590 3350.4903 3344.4391 1.7793
+ 2685.0209 2684.0255 2688.4638 2683.0311 1.9015
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 3.768 seconds)
-
-
.. _sphx_glr_download_how_to_deploy_models_deploy_model_on_adreno.py:
.. only:: html
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 f0b9768cb4..dfa7053387 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -437,7 +437,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.6146 16.4764 17.1486 16.2948 0.3198
+ 15.5922 15.5360 15.8489 15.4871 0.1193
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 6bebe678da..8ab1bbf3b0 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]
5%|4 | 7.99M/170M [00:00<00:02, 79.8MB/s]
10%|9 | 16.8M/170M [00:00<00:02, 76.4MB/s]
14%|#4 | 24.1M/170M [00:00<00:02, 59.1MB/s]
19%|#8 | 32.0M/170M [00:00<00:02, 65.3MB/s]
28%|##8 | 48.1M/170M [00:00<00:01, 95.5MB/s]
34%|###4 | 58.0M/170M [00:00<00:01, 90.6MB/s]
40%|###9 | 67.4M/170M [00:00<00:01, 92.8MB/s]
46%|####5 | 77.8M/170M [00:00<00:00, 97.3MB/s]
51%|#####1 | 87.3M/170M [00:01<00:00, 94.8MB/s]
57%|#####6 | 96.5M/170M [00:01<00:00, 84.0MB/s]
62%|######1 | 105M/170M [00:01<00:00, 78.4MB/s]
70%|######9 | 118M/170M [00:01<00:00, 94.9MB/s]
75%|#######5 | 128M/170M [00:01<00:00, 93.1MB/s]
85%|########4 | 144M/170M [00:01<00:00, 104MB/s]
94%|#########4| 160M/170M [00:01<00:00, 107MB/s]
100%|##########| 170M/170M [00:01<00:00, 93.5MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
5%|4 | 7.99M/170M [00:00<00:02, 64.5MB/s]
9%|9 | 16.0M/170M [00:00<00:02, 69.0MB/s]
14%|#4 | 24.0M/170M [00:00<00:02, 71.5MB/s]
19%|#8 | 32.0M/170M [00:00<00:01, 75.2MB/s]
24%|##3 | 40.0M/170M [00:00<00:01, 71.0MB/s]
28%|##8 | 48.0M/170M [00:00<00:01, 74.5MB/s]
35%|###4 | 59.3M/170M [00:00<00:01, 87.9MB/s]
41%|####1 | 70.0M/170M [00:00<00:01, 95.2MB/s]
47%|####7 | 80.0M/170M [00:01<00:01, 90.9MB/s]
52%|#####2 | 88.8M/170M [00:01<00:01, 62.6MB/s]
57%|#####6 | 96.0M/170M [00:01<00:01, 64.9MB/s]
62%|######1 | 104M/170M [00:01<00:00, 70.6MB/s]
69%|######8 | 116M/170M [00:01<00:00, 84.3MB/s]
74%|#######3 | 125M/170M [00:01<00:00, 59.1MB/s]
78%|#######7 | 132M/170M [00:02<00:00, 57.3MB/s]
85%|########4 | 144M/170M [00:02<00:00, 64.4MB/s]
89%|########9 | 152M/170M [00:02<00:00, 60.5MB/s]
96%|#########5| 163M/170M [00:02<00:00, 71.2MB/s]
100%|##########| 170M/170M [00:02<00:00, 71.5MB/s]
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torch/nn/functional.py:3897: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/venv/apache-tvm-py3.7/lib/python3.7/site-packages/torchvision/models/detection/anchor_utils.py:124: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -299,7 +299,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 28.890 seconds)
+ **Total running time of the script:** ( 3 minutes 22.255 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 d48d7eafc5..90892d21d4 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, 53.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 79.0MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
59%|#####8 | 7.99M/13.6M [00:00<00:00, 50.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 53.9MB/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)
- 90.3870 90.3335 91.4580 90.0791 0.2373
+ 90.1450 90.0606 94.1685 89.8995 0.4423
@@ -458,7 +458,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.948 seconds)
+ **Total running time of the script:** ( 1 minutes 11.751 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 3376f7f966..1fb4f632e0 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)
- 119.7224 119.5941 126.5624 118.7859 0.8033
+ 118.1641 118.2210 119.2519 117.1100 0.4611
@@ -460,7 +460,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 27.495 seconds)
+ **Total running time of the script:** ( 2 minutes 36.709 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 6eedcf92f4..9cb9fd5e12 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 37.716 seconds)
+ **Total running time of the script:** ( 1 minutes 42.416 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 d0bf9850a3..3d3e1e7c4b 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]
3%|2 | 3977/132723 [00:00<00:03, 39762.26KB/s]
8%|7 | 10187/132723 [00:00<00:02, 52898.27KB/s]
14%|#3 | 17918/132723 [00:00<00:01, 64040.15KB/s]
19%|#9 | 25691/132723 [00:00<00:01, 69441.97KB/s]
25%|##5 | 33518/132723 [00:00<00:01, 72618.09KB/s]
31%|###1 | 41336/132723 [00:00<00:01, 74499.47KB/s]
37%|###7 | 49119/132723 [00:00<00:01, 75586.38KB/s]
43%|####2 | 56958/132723 [00:00<00:00, 76472.50KB/s]
49%|####8 | 64805/132723 [00:00<00:00, 77094.01KB/s]
55%|#####4 | 72585/132723 [00:01<00:00, 77263.00KB/s]
61%|###### | 80376/132723 [00:01<00:00, 77457.77KB/s]
66%|######6 | 88181/132723 [00:01<00:00, 77635.69KB/s]
72%|#######2 | 95977/132723 [00:01<00:00, 77730.00KB/s]
78%|#######8 | 103817/132723 [00:01<00:00, 77930.27KB/s]
84%|########4 | 111617/132723 [00:01<00:00, 77948.17KB/s]
90%|########9
| 119412/132723 [00:01<00:00, 77758.10KB/s]
96%|#########5| 127199/132723 [00:01<00:00, 77783.08KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74925.02KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5640/132723 [00:00<00:02, 56397.90KB/s]
10%|9 | 12997/132723 [00:00<00:01, 66494.82KB/s]
16%|#5 | 20598/132723 [00:00<00:01, 70834.49KB/s]
21%|##1 | 28475/132723 [00:00<00:01, 73963.67KB/s]
27%|##7 | 36366/132723 [00:00<00:01, 75715.09KB/s]
33%|###3 | 44179/132723 [00:00<00:01, 76534.74KB/s]
39%|###9 | 51985/132723 [00:00<00:01, 77030.29KB/s]
45%|####5 | 59828/132723 [00:00<00:00, 77473.83KB/s]
51%|##### | 67646/132723 [00:00<00:00, 77692.56KB/s]
57%|#####6 | 75558/132723 [00:01<00:00, 78131.71KB/s]
63%|######2 | 83372/132723 [00:01<00:00, 77757.85KB/s]
69%|######8 | 91186/132723 [00:01<00:00, 77866.92KB/s]
75%|#######4 | 99068/132723 [00:01<00:00, 78153.94KB/s]
81%|######## | 106946/132723 [00:01<00:00, 78337.39KB/s]
86%|########6 | 114780/132723 [00:01<00:00, 78271.51KB/s]
92%|#########
2| 122672/132723 [00:01<00:00, 78465.54KB/s]
98%|#########8| 130574/132723 [00:01<00:00, 78630.60KB/s]
100%|##########| 132723/132723 [00:01<00:00, 76781.09KB/s]
@@ -246,7 +246,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 34.247 seconds)
+ **Total running time of the script:** ( 3 minutes 25.637 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 00c2e47fb3..4de9a86a04 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**15:01.394** total execution time for **how_to_deploy_models** files:
+**14:45.499** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:34.247 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 03:25.637 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:28.890 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:22.255 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:27.495 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:36.709 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:37.716 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:42.416 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:13.948 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:11.751 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 01:03.768 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_adreno.py` (``deploy_model_on_adreno.py``) | 00:54.388 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:41.008 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:39.185 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:27.437 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:26.705 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.879 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:26.447 | 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 a7dc111481..a5fac33eea 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.zipef6b2f36-e7aa-42bb-a715-69b30a51e523 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb9b11189-fcad-489c-b4dc-d59850bff597 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 d93522c01f..fca367e89c 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
=================
-**00:52.757** total execution time for **how_to_extend_tvm** files:
+**00:51.322** 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``) | 00:48.939 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:47.694 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.713 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.577 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.044 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index bb62ecfb4c..dff3a01f3b 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: 18444us [18444us] (48.44%; 48.44%)
- FoldScaleAxis: 19634us [8us] (51.56%; 51.56%)
- FoldConstant: 19625us [1724us] (51.54%; 99.96%)
- InferType: 17901us [17901us] (47.01%; 91.21%)
+ InferType: 17965us [17965us] (48.54%; 48.54%)
+ FoldScaleAxis: 19042us [6us] (51.46%; 51.46%)
+ FoldConstant: 19035us [1705us] (51.44%; 99.97%)
+ InferType: 17330us [17330us] (46.83%; 91.04%)
@@ -262,10 +262,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 18098us [18098us] (47.97%; 47.97%)
- FoldScaleAxis: 19626us [8us] (52.03%; 52.03%)
- FoldConstant: 19618us [1758us] (52.00%; 99.96%)
- InferType: 17860us [17860us] (47.34%; 91.04%)
+ InferType: 17388us [17388us] (47.56%; 47.56%)
+ FoldScaleAxis: 19173us [5us] (52.44%; 52.44%)
+ FoldConstant: 19168us [1688us] (52.43%; 99.98%)
+ InferType: 17481us [17481us] (47.81%; 91.20%)
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 bbf734a0b9..6f018adc08 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -331,7 +331,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.186111 ms
+ Convolution: 54.126304 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 26c00dcd78..921714fdee 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -608,7 +608,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.831319 ms
+ conv2d with tensor core: 6.691885 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 53417387db..8f310f60de 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: 0.019284
- Baseline: 3.462858
+ Numpy running time: 0.019105
+ Baseline: 3.258741
@@ -227,7 +227,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.305168
+ Opt1: 0.298000
@@ -318,7 +318,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.338542
+ Opt2: 0.332539
@@ -406,7 +406,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117760
+ Opt3: 0.114561
@@ -523,7 +523,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110228
+ Opt4: 0.108607
@@ -635,7 +635,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111027
+ Opt5: 0.111281
@@ -748,7 +748,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.148403
+ Opt6: 0.146370
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 436c54be11..8552524fd5 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.190** total execution time for **how_to_optimize_operators** files:
+**00:34.377** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.707 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.833 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.429 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.469 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.055 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.076 | 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 087159f658..6a6f84c082 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**09:38.124** total execution time for **how_to_tune_with_autoscheduler** files:
+**09:08.538** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:42.968 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 05:29.796 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:39.009 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:37.055 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:05.952 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 01:04.667 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:43.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:30.964 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:14.250 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:13.513 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:12.923 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:12.544 | 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 942ff0dfaa..17c88d7272 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
@@ -245,307 +245,481 @@ cooperative fetching, unrolling and operator fusion.
bias_1 = T.match_buffer(bias, (1, 512, 1, 1))
compute_1 = T.match_buffer(compute, (1, 512, 7, 7))
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 16)
- conv2d_nchw = T.allocate([28], "float32", "local")
- pad_temp_shared = T.allocate([2016], "float32", "shared")
+ 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.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 56)
- conv2d_nchw_1 = T.buffer_decl((4,), data=conv2d_nchw, scope="local", align=8)
+ T.launch_thread(threadIdx_x, 64)
+ conv2d_nchw_1 = T.buffer_decl((14,), data=conv2d_nchw, scope="local", align=32)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[14] = T.float32(0)
- conv2d_nchw_1[16] = T.float32(0)
- conv2d_nchw_1[18] = T.float32(0)
- conv2d_nchw_1[20] = T.float32(0)
- conv2d_nchw_1[22] = T.float32(0)
- conv2d_nchw_1[24] = T.float32(0)
- conv2d_nchw_1[26] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
+ conv2d_nchw_1[2] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[13] = T.float32(0)
- conv2d_nchw_1[15] = T.float32(0)
- conv2d_nchw_1[17] = T.float32(0)
- conv2d_nchw_1[19] = T.float32(0)
- conv2d_nchw_1[21] = T.float32(0)
- conv2d_nchw_1[23] = T.float32(0)
- conv2d_nchw_1[25] = T.float32(0)
- conv2d_nchw_1[27] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(16, 3):
- cse_var_4: T.int32 = rc_outer_outer * 1568
- cse_var_3: T.int32 = rc_outer_outer * 288
- cse_var_2: T.int32 = ry_outer_outer * 7
+ 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
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.buffer_decl((2016,), data=pad_temp_shared, scope="shared")
- data_2 = T.buffer_decl((25088,), data=data_1.data)
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 < threadIdx_x_1 * 6 % 9 and threadIdx_x_1 * 6 % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + threadIdx_x_1 * 6 % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 1) % 9 and (threadIdx_x_1 * 6 + 1) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 1) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 2] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 2) % 9 and (threadIdx_x_1 * 6 + 2) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 2) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 3] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 3) % 9 and (threadIdx_x_1 * 6 + 3) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 4] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 4) % 9 and (threadIdx_x_1 * 6 + 4) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 5] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 5) % 9 and (threadIdx_x_1 * 6 + 5) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 5) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 336] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 3) % 9 and (threadIdx_x_1 * 6 + 3) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 112) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 337] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 4) % 9 and (threadIdx_x_1 * 6 + 4) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 112) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 338] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 5) % 9 and (threadIdx_x_1 * 6 + 5) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 112) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 5) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 339] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 6) % 9 and (threadIdx_x_1 * 6 + 6) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 113) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 340] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 7) % 9 and (threadIdx_x_1 * 6 + 7) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 113) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 341] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 8) % 9 and (threadIdx_x_1 * 6 + 8) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 113) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 672] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 6) % 9 and (threadIdx_x_1 * 6 + 6) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 224) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 673] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 7) % 9 and (threadIdx_x_1 * 6 + 7) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 224) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 674] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 8) % 9 and (threadIdx_x_1 * 6 + 8) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 224) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 8) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 675] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 < threadIdx_x_1 * 6 % 9 and threadIdx_x_1 * 6 % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + threadIdx_x_1 * 6 % 9 + 517], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 676] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 <= (threadIdx_x_1 * 6 + 1) % 9 and (threadIdx_x_1 * 6 + 1) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 1) % 9 + 517], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 677] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 < (threadIdx_x_1 * 6 + 2) % 9 and (threadIdx_x_1 * 6 + 2) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 2) % 9 + 517], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1008] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 < threadIdx_x_1 * 6 % 9 and threadIdx_x_1 * 6 % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + threadIdx_x_1 * 6 % 9 + 776], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1009] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 1) % 9 and (threadIdx_x_1 * 6 + 1) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 1) % 9 + 776], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1010] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 2) % 9 and (threadIdx_x_1 * 6 + 2) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 2) % 9 + 776], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1011] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 3) % 9 and (threadIdx_x_1 * 6 + 3) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 337) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1012] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 4) % 9 and (threadIdx_x_1 * 6 + 4) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 337) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1013] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 5) % 9 and (threadIdx_x_1 * 6 + 5) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 337) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 5) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1344] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 3) % 9 and (threadIdx_x_1 * 6 + 3) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 448) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1345] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 4) % 9 and (threadIdx_x_1 * 6 + 4) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 448) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1346] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 5) % 9 and (threadIdx_x_1 * 6 + 5) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 448) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 5) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1347] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 6) % 9 and (threadIdx_x_1 * 6 + 6) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 449) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1348] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 7) % 9 and (threadIdx_x_1 * 6 + 7) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 449) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1349] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 8) % 9 and (threadIdx_x_1 * 6 + 8) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 449) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1680] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 6) % 9 and (threadIdx_x_1 * 6 + 6) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 560) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1681] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 7) % 9 and (threadIdx_x_1 * 6 + 7) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 560) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1682] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 8) % 9 and (threadIdx_x_1 * 6 + 8) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 560) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 8) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1683] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 < threadIdx_x_1 * 6 % 9 and threadIdx_x_1 * 6 % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + threadIdx_x_1 * 6 % 9 + 1301], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1684] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 <= (threadIdx_x_1 * 6 + 1) % 9 and (threadIdx_x_1 * 6 + 1) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 1) % 9 + 1301], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1685] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 < (threadIdx_x_1 * 6 + 2) % 9 and (threadIdx_x_1 * 6 + 2) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 2) % 9 + 1301], T.float32(0))
+ pad_temp_shared_1 = T.buffer_decl((72,), data=pad_temp_shared, scope="shared")
+ with T.launch_thread(threadIdx_x_1, 64):
+ data_2 = T.buffer_decl((25088,), data=data_1.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_2[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_2[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_2[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_2[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_2 = T.env_thread("threadIdx.x")
kernel_shared_1 = T.buffer_decl((3072,), data=kernel_shared, scope="shared")
kernel_2 = T.buffer_decl((2359296,), data=kernel_1.data)
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 56] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 56) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 112] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 112) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 168] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 168) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 224] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 280] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 280) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 336] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 336) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 392] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 392) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 448] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 504] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 504) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 8) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 560] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 560) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 616] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 616) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 40) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 32256]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 728] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 728) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 784] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 784) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 840] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 840) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 896] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 896) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 952] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 952) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1008] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1008) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1064] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1064) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1120] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1120) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1176] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1176) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 8) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1232] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1232) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1288] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1288) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 40) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1344] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 64512]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1400] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1400) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1456] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1456) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1512] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1512) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1568] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1568) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1624] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1624) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1680] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1680) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1736] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1736) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1792] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1792) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1848] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1848) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 8) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1904] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1904) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1960] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1960) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 40) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2016] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 96768]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2072] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2072) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2128] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2128) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2184] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2184) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2240] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2240) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2296] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2296) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2352] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2352) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2408] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2408) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2464] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2464) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2520] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2520) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 8) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2576] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2576) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2632] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2632) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 40) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2688] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 129024]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2744] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2744) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2800] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2800) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2856] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2856) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2912] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2912) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2968] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2968) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- if T.likely(threadIdx_x_2 < 48):
- kernel_shared_1[threadIdx_x_2 + 3024] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 3024) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- for rc_outer_inner in range(32):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- for i1_inner in range(2):
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 64] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 64) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 128] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 128) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 192] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 36864]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 256] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 256) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 320] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 320) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 384] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 73728]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 448] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 448) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 512] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 512) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 576] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 110592]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 640] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 640) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 704] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 704) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 768] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 147456]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 832] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 832) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 896] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 896) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 960] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 184320]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1024] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1024) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1088] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1088) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1152] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 221184]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1216] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1216) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1280] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1280) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1344] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 258048]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1408] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1408) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1472] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1472) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1536] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 294912]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1600] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1600) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1664] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1664) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1728] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 331776]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1792] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1792) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1856] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1856) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1920] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 368640]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1984] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1984) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2048] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2048) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2112] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 405504]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2176] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2176) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2240] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2240) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2304] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 442368]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2368] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2368) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2432] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2432) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2496] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 479232]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2560] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2560) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2624] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2624) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2688] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 516096]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2752] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2752) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2816] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2816) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2880] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 552960]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2944] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2944) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 3008] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 3008) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 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_2 = T.buffer_decl((25088,), data=compute_1.data)
bias_2 = T.buffer_decl((512,), data=bias_1.data)
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7] = T.max(conv2d_nchw_1[i1_inner] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 1] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 2] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 3] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 4] = T.max(conv2d_nchw_1[i1_inner + 8] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 5] = T.max(conv2d_nchw_1[i1_inner + 10] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 6] = T.max(conv2d_nchw_1[i1_inner + 12] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 784] = T.max(conv2d_nchw_1[i1_inner + 14] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 785] = T.max(conv2d_nchw_1[i1_inner + 16] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 786] = T.max(conv2d_nchw_1[i1_inner + 18] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 787] = T.max(conv2d_nchw_1[i1_inner + 20] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 788] = T.max(conv2d_nchw_1[i1_inner + 22] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 789] = T.max(conv2d_nchw_1[i1_inner + 24] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 790] = T.max(conv2d_nchw_1[i1_inner + 26] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
+ compute_2[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_2[blockIdx_x // 7 * 128 + threadIdx_x * 2 + i1_inner], T.float32(0))
@@ -595,7 +769,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.315 ms
+ Execution time of this operator: 0.354 ms
@@ -645,35 +819,35 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_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=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_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=7)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+ conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_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=8)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ compute_i1_o_o_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=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_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=7)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -692,14 +866,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ 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=6)
+ 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=56)
+ 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", 1024)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -717,238 +891,430 @@ 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__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[28];
- __shared__ float pad_temp_shared[2016];
+ 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[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
- conv2d_nchw[22] = 0.000000e+00f;
- conv2d_nchw[24] = 0.000000e+00f;
- conv2d_nchw[26] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
- conv2d_nchw[21] = 0.000000e+00f;
- conv2d_nchw[23] = 0.000000e+00f;
- conv2d_nchw[25] = 0.000000e+00f;
- conv2d_nchw[27] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ 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();
- pad_temp_shared[(((int)threadIdx.x) * 6)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 2)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 336)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 112) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 337)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 112) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 338)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 112) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 339)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 113) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 340)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 113) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 341)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 113) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 672)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 224) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 673)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 224) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 674)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 224) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 675)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) + 517)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 676)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) + 517)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 677)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) + 517)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1008)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1009)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1010)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1011)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 337) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1012)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 337) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1013)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 337) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1344)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 448) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1345)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 448) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1346)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 448) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1347)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 449) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1348)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 449) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1349)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 449) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1680)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 560) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1681)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 560) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1682)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 560) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1683)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) + 1301)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1684)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) + 1301)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1685)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) + 1301)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ 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);
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
+ 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 784)] = max((conv2d_nchw[(i1_inner + 14)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 785)] = max((conv2d_nchw[(i1_inner + 16)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 786)] = max((conv2d_nchw[(i1_inner + 18)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 787)] = max((conv2d_nchw[(i1_inner + 20)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 788)] = max((conv2d_nchw[(i1_inner + 22)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 789)] = max((conv2d_nchw[(i1_inner + 24)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 790)] = max((conv2d_nchw[(i1_inner + 26)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 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);
+ }
}
}
@@ -1010,7 +1376,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 5 minutes 42.968 seconds)
+ **Total running time of the script:** ( 5 minutes 29.796 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 24475c9685..82a84a89fe 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8608 7.8596 7.8690 7.8538 0.0063
+ 7.8726 7.8762 7.8767 7.8649 0.0054
@@ -675,7 +675,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.952 seconds)
+ **Total running time of the script:** ( 1 minutes 4.667 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 17816cb203..fa1543e64b 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)
- 763.9441 763.1073 767.3202 761.4047 2.4864
+ 744.6278 743.8504 746.7951 743.2380 1.5527
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 39.009 seconds)
+ **Total running time of the script:** ( 1 minutes 37.055 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 b9a2ae7c1f..a318ead3ce 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
@@ -509,7 +509,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.728 ms
+ Execution time of this operator: 1.716 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 2e8e5fc7bd..23e6ea39be 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
=================
-**00:32.327** total execution time for **how_to_tune_with_autotvm** files:
+**00:37.938** 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``) | 00:32.294 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:37.906 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.018 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``) | 00:00.004 | 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_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 710b87bf02..6d90968ad0 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -268,7 +268,8 @@ for this template
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ No: 1 GFLOPS: 111.35/111.35 result: MeasureResult(costs=(0.0020790124897959185,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7945833206176758, timestamp=1674022602.5026455) [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,979530
+ No: 2 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -390,8 +391,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8611762
- No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8198569
+ No: 3 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -513,8 +514,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4044736
- No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2580687
+ No: 4 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -636,8 +637,26 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,373192
- No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10439569
+ No: 5 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+ TimeoutError
+
+ [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2949493
+ No: 6 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -759,8 +778,8 @@ 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, 64, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4184726
- No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2547744
+ No: 7 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -882,8 +901,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1713268
- No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8904508
+ No: 8 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1005,8 +1024,8 @@ 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, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1452744
- No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6608963
+ No: 9 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1128,9 +1147,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7466854
- No: 8 GFLOPS: 9.05/9.05 result: MeasureResult(costs=(0.025575887500000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4544157981872559, timestamp=1674000444.1167586) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,292278
- No: 9 GFLOPS: 0.00/9.05 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9258557
+ No: 10 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1252,8 +1270,8 @@ 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, 1, 7, 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', 0)],None,4678616
- No: 10 GFLOPS: 0.00/9.05 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9603335
+ No: 11 GFLOPS: 0.00/111.35 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
@@ -1375,9 +1393,8 @@ 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, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7654200
- No: 11 GFLOPS: 37.37/37.37 result: MeasureResult(costs=(0.0061950823600000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.392481803894043, timestamp=1674000445.7371573) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6497947
- No: 12 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2587768
+ No: 12 GFLOPS: 0.00/111.35 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 +1516,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4454169
- No: 13 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,736315
+ No: 13 GFLOPS: 0.00/111.35 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 +1639,8 @@ 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, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6840785
- No: 14 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10044555
+ No: 14 GFLOPS: 0.00/111.35 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 +1762,8 @@ 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, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2304695
- No: 15 GFLOPS: 1.62/37.37 result: MeasureResult(costs=(0.143244812,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.765275716781616, timestamp=1674000454.710923) [('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1948741
- No: 16 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6348485
+ No: 15 GFLOPS: 0.00/111.35 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 +1885,8 @@ 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, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7841992
- No: 17 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7624397
+ No: 16 GFLOPS: 0.00/111.35 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
@@ -1992,8 +2008,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3958997
- No: 18 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 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,4848126
+ No: 17 GFLOPS: 0.00/111.35 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
@@ -2115,8 +2131,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3989510
- No: 19 GFLOPS: 0.00/37.37 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, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7195926
+ No: 18 GFLOPS: 0.00/111.35 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
@@ -2238,8 +2254,8 @@ 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5790861
- No: 20 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2240121
+ No: 19 GFLOPS: 0.00/111.35 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
@@ -2361,7 +2377,8 @@ for this template
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
- tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7774715
+ tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9268500
+ No: 20 GFLOPS: 234.57/234.57 result: MeasureResult(costs=(0.0009869387213114753,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.453100681304932, timestamp=1674022621.5645502) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7851432
@@ -2416,9 +2433,9 @@ and measure running time.
Finish loading 20 records
Best config:
- [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6497947
+ [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7851432
Finish loading 20 records
- Time cost of this operator: 0.006520
+ Time cost of this operator: 0.001165
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 b18cde4cb4..bf76d56af5 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
@@ -363,10 +363,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.4 98.744 (1, 2, 10, 10, 3) 2 1 [315.4]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.946 (1, 6, 10, 10) 1 1 [3.021]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.99 0.31 (1, 1, 10, 10, 3) 1 1 [0.99]
- Total_time - 319.411 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.2 98.702 (1, 2, 10, 10, 3) 2 1 [308.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.09 0.99 (1, 6, 10, 10) 1 1 [3.09]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.965 0.309 (1, 1, 10, 10, 3) 1 1 [0.965]
+ Total_time - 312.254 - - - - -
@@ -431,10 +431,10 @@ 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 102.5 97.46 (1, 6, 10, 10, 1) 2 1 [102.5]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.805 1.716 (1, 6, 10, 10) 1 1 [1.805]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.867 0.824 (1, 3, 10, 10, 1) 1 1 [0.867]
- Total_time - 105.172 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.1 97.36 (1, 6, 10, 10, 1) 2 1 [100.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 1.703 (1, 6, 10, 10) 1 1 [1.75]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.938 (1, 1, 10, 10, 3) 1 1 [0.964]
+ Total_time - 102.814 - - - - -
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 a742e45936..9523bbadfd 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
@@ -117,7 +117,7 @@ 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, 51.5MB/s]
+
0%| | 0.00/3.42M [00:00<?, ?B/s]
100%|##########| 3.42M/3.42M [00:00<00:00, 71.2MB/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.
@@ -322,7 +322,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.838 seconds)
+ **Total running time of the script:** ( 1 minutes 7.816 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 bf58d39d76..fd5dc458fb 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -218,7 +218,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp5iwbtdqy/images/random'
+ '/tmp/tmpdfofimzq/images/random'
@@ -309,7 +309,7 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. image-sg:: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
- :alt: [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]
+ :alt: [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0]
:srcset: /how_to/work_with_microtvm/images/sphx_glr_micro_train_001.png
:class: sphx-glr-single-img
@@ -318,8 +318,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp5iwbtdqy/images/target contains 8144 images
- /tmp/tmp5iwbtdqy/images/random contains 5000 images
+ /tmp/tmpdfofimzq/images/target contains 8144 images
+ /tmp/tmpdfofimzq/images/random contains 5000 images
@@ -494,13 +494,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 47s - loss: 0.2298 - accuracy: 0.9200 - val_loss: 0.1528 - val_accuracy: 0.9551 - 47s/epoch - 145ms/step
+ 328/328 - 47s - loss: 0.2342 - accuracy: 0.9197 - val_loss: 0.1264 - val_accuracy: 0.9532 - 47s/epoch - 143ms/step
Epoch 2/3
- 328/328 - 44s - loss: 0.1025 - accuracy: 0.9607 - val_loss: 0.1187 - val_accuracy: 0.9694 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.1031 - accuracy: 0.9623 - val_loss: 0.1160 - val_accuracy: 0.9532 - 43s/epoch - 131ms/step
Epoch 3/3
- 328/328 - 44s - loss: 0.0705 - accuracy: 0.9750 - val_loss: 0.1366 - val_accuracy: 0.9619 - 44s/epoch - 133ms/step
+ 328/328 - 43s - loss: 0.0653 - accuracy: 0.9745 - val_loss: 0.1150 - val_accuracy: 0.9600 - 43s/epoch - 131ms/step
- <keras.callbacks.History object at 0x7f57f1b84410>
+ <keras.callbacks.History object at 0x7f2087634f90>
@@ -857,7 +857,7 @@ 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:** ( 5 minutes 23.445 seconds)
+ **Total running time of the script:** ( 4 minutes 45.460 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 6694c6eb0a..83e3ae9702 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**07:40.955** total execution time for **how_to_work_with_microtvm** files:
+**06:55.995** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:23.445 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:45.460 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:10.838 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_pytorch.py` (``micro_pytorch.py``) | 01:07.816 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:53.689 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:50.563 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:09.003 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.439 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.980 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.716 | 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 bcf21e6958..91d4bd53ca 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.768** total execution time for **how_to_work_with_relay** files:
+**00:43.054** 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``) | 00:32.755 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.577 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.407 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.963 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.601 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.508 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index c4bf528877..320b394aad 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -264,7 +264,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f57f227d8c0>
+ <function my_cuda_math_rule at 0x7f2087e5d9e0>
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 54ea935035..c48c5b2b2c 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
=================
-**00:07.050** total execution time for **how_to_work_with_schedules** files:
+**00:04.522** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:04.483 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.165 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.208 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.088 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.579 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.534 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.559 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.515 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.116 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.050 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.049 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.031 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.024 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.023 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 25efb5bc50..05280171c9 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -340,7 +340,7 @@ The importing needs to happen before the tensorized GEMV being executed.
B_1 = T.match_buffer(B, (512, 64))
C_1 = T.match_buffer(C, (1024, 512))
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmp8mz2ijcq/input0.cc'\nsource_filename = \"/tmp/tmp8mz2ijcq/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca float*, [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpa__vx31f/input0.cc'\nsource_filename = \"/tmp/tmpa__vx31f/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca float*, [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C_1.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A_1.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B_1.data, j_outer * 1024, 1024, 1), 16, 64, 64)
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 08cd0cf924..7bc70c78a2 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
=================
-**00:30.395** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:29.221** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:30.388 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:29.215 | 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 9b32d8afa5..271646101c 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 32.78s!
+ resnet18_v1 inference graph built in 31.10s!
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 7bb6a832d3..18e0adc26a 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 22.33s!
+ yolov3-tiny inference graph built in 21.25s!
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 3827e5f06b..7b430e89da 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
=================
-**01:39.096** total execution time for **topic_vta_tutorials_frontend** files:
+**01:35.883** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:49.648 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.072 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.448 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:47.811 | 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 9c043a29b9..529f62772c 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
=================
-**00:03.150** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.075** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.679 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.657 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.471 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.418 | 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 0470696040..f9b6b55da1 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
=================
-**00:00.833** total execution time for **topic_vta_tutorials** files:
+**00:00.777** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.450 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.427 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.383 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.349 | 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 424003942b..cf50be6d5d 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -211,12 +211,12 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
- *E
.T
+
.. GENERATED FROM PYTHON SOURCE LINES 133-139
Inspecting the Optimized Schedule
@@ -326,7 +326,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.022 ms
+ Execution time of this operator: 94.901 ms
@@ -444,7 +444,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 38.354 seconds)
+ **Total running time of the script:** ( 1 minutes 29.212 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 3175545c0c..6edb23bd3c 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: 10.12/10.12 result: MeasureResult(costs=(0.026523687400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6611154079437256, timestamp=1673998892.190876) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
- No: 2 GFLOPS: 9.29/10.12 result: MeasureResult(costs=(0.028901774400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7235610485076904, timestamp=1673998893.6952832) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
- No: 3 GFLOPS: 8.27/10.12 result: MeasureResult(costs=(0.0324548154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7526891231536865, timestamp=1673998894.4671183) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
- No: 4 GFLOPS: 12.49/12.49 result: MeasureResult(costs=(0.0214984956,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5797519683837891, timestamp=1673998895.863199) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
- No: 5 GFLOPS: 11.64/12.49 result: MeasureResult(costs=(0.023065638399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6571595668792725, timestamp=1673998896.7626605) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
- No: 6 GFLOPS: 8.58/12.49 result: MeasureResult(costs=(0.031269829,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9039361476898193, timestamp=1673998898.3122692) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
- No: 7 GFLOPS: 2.25/12.49 result: MeasureResult(costs=(0.11905661940000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1431119441986084, timestamp=1673998900.4692845) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
- No: 8 GFLOPS: 12.77/12.77 result: MeasureResult(costs=(0.0210180726,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5991122722625732, timestamp=1673998901.062802) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
- No: 9 GFLOPS: 0.89/12.77 result: MeasureResult(costs=(0.3003506016,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.006605863571167, timestamp=1673998906.194126) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
- No: 10 GFLOPS: 0.50/12.77 result: MeasureResult(costs=(0.5337017275999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.752919673919678, timestamp=1673998914.984868) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
+ No: 1 GFLOPS: 2.42/2.42 result: MeasureResult(costs=(0.11078919699999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0058329105377197, timestamp=1674021106.6407683) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+ No: 2 GFLOPS: 12.39/12.39 result: MeasureResult(costs=(0.0216594874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5815625190734863, timestamp=1674021107.9928033) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+ No: 3 GFLOPS: 1.79/12.39 result: MeasureResult(costs=(0.1502231728,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.643393039703369, timestamp=1674021111.4178398) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 4 GFLOPS: 2.03/12.39 result: MeasureResult(costs=(0.1321356942,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.333951711654663, timestamp=1674021113.7726407) [('tile_y', [-1, 256]), ('tile_x', [-1, 4])],None,28
+ No: 5 GFLOPS: 10.96/12.39 result: MeasureResult(costs=(0.024493366199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.619408369064331, timestamp=1674021114.6219072) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+ No: 6 GFLOPS: 3.27/12.39 result: MeasureResult(costs=(0.08203405239999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5492236614227295, timestamp=1674021116.1835446) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
+ No: 7 GFLOPS: 12.80/12.80 result: MeasureResult(costs=(0.020977112399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6758532524108887, timestamp=1674021117.5373123) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+ No: 8 GFLOPS: 12.95/12.95 result: MeasureResult(costs=(0.020725559400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5682404041290283, timestamp=1674021118.123468) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
+ No: 9 GFLOPS: 13.87/13.87 result: MeasureResult(costs=(0.019353842399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.534494161605835, timestamp=1674021118.773921) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+ No: 10 GFLOPS: 0.90/13.87 result: MeasureResult(costs=(0.2990334894,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.992733716964722, timestamp=1674021123.8084934) [('tile_y', [-1, 128]), ('tile_x', [-1, 2])],None,17
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 1c93c387ad..6a1cad13f4 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': 517.6232956799993, 'median': 517.659318699998, 'std': 1.5351246130381426}
+ {'mean': 514.1060797499813, 'median': 513.3606129998952, 'std': 2.953015519281599}
@@ -545,31 +545,30 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 11.79/ 16.28 GFLOPS | Progress: (4/20) | 7.91 s
[Task 1/25] Current/Best: 22.54/ 23.10 GFLOPS | Progress: (8/20) | 12.50 s
[Task 1/25] Current/Best: 12.61/ 23.10 GFLOPS | Progress: (12/20) | 16.99 s
[Task 1/25] Current/Best: 22.76/ 23.10 GFLOPS | Progress: (16/20) | 20.39 s
[Task 1/25] Current/Best: 3.42/ 23.10 GFLOPS | Progress: (20/20) | 23.62 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.07/ 19.79 GFLOPS | Progress: (4/20) | 3.24 s
[Task 2/25] Current/Best: 19.18/ 19.79 GFLOPS | Progress: (8/20) | 5.03 s
[Task 2/25] Current/Best: 9.15/ 22.12 GFLOPS | Progress: (12/20) | 6.55 s
[Task 2/25] Current/Best: 12.93/ 22.12 GFLOPS | Progress: (16/20) | 8.32 s
[Task 2/25] Current/Best: 14.06/ 22.12 GFLOPS | Progress: (20/20) | 10.28 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 11.01 GFLOPS | Progress: (4/20) | 7.09 s
[Task 3/25] Current/Best: 6.39/ 18.27 GFLOPS | Progress: (8/20) | 9.74 s
[Task 3/25] Current/Best: 6.21/ 22.38 GFLOPS | Progress: (12/20) | 11.88 s
[Task 3/25] Current/Best: 22.74/ 22.74 GFLOPS | Progress: (16/20) | 14.23 s
[Task 3/25] Current/Best: 19.38/ 22.74 GFLOPS | Progress: (20/20) | 16.54 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 15.17/ 15.17 GFLOPS | Progress: (4/20) | 6.57 s
[Task 4/25] Current/Best: 12.11/ 15.17 GFLOPS | Progress: (8/20) | 11.12 s
[Task 4/25] Current/Best: 15.74/ 15.74 GFLOPS | Progress: (12/20) | 12.98 s
[Task 4/25] Current/Best: 16.44/ 17.27 GFLOPS | Progress: (16/20) | 15.70 s
[Task 4/25] Current/Best: 14.37/ 17.27 GFLOPS | Progress: (20/20) | 19.93 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.74/ 14.43 GFLOPS | Progress: (4/20) | 3.68 s
[Task 5/25] Current/Best: 15.84/ 15.84 GFLOPS | Progress: (8/20) | 5.70 s
[Task 5/25] Current/Best: 12.14/ 21.83 GFLOPS | Progress: (12/20) | 7.73 s
[Task 5/25] Current/Best: 6.25/ 21.83 GFLOPS | Progress: (16/20) | 10.50 s
[Task 5/25] Current/Best: 9.02/ 21.83 GFLOPS | Progress: (20/20) | 13.63 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 5.19/ 14.42 GFLOPS | Progress: (4/20) | 5.47 s
[Task 6/25] Current/Best: 10.73/ 18.61 GFLOPS | Progress: (8/20) | 8.10 s
[Task 6/25] Current/Best: 12.93/ 18.61 GFLOPS | Progress: (12/20) | 11.49 s
[Task 6/25] Current/Best: 5.58/ 18.61 GFLOPS | Progress: (16/20) | 14.90 s
[Task 6/25] Current/Best: 6.08/ 18.61 GFLOPS | Progress: (20/20) | 20.54 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 16.97/ 19.07 GFLOPS | Progress: (4/20) | 4.77 s
[Task 7/25] Current/Best: 15.25/ 19.07 GFLOPS | Progress: (8/20) | 6.97 s
[Task 7/25] Current/Best: 8.27/ 19.07 GFLOPS | Progress: (12/20) | 9.59 s
[Task 7/25] Current/Best: 10.79/ 19.91 GFLOPS | Progress: (16/20) | 12.55 s
[Task 7/25] Current/Best: 15.32/ 19.91 GFLOPS | Progress: (20/20) | 15.39 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 2.49/ 10.53 GFLOPS | Progress: (4/20) | 10.31 s
[Task 8/25] Current/Best: 12.41/ 12.41 GFLOPS | Progress: (8/20) | 16.36 s
[Task 8/25] Current/Best: 7.69/ 18.34 GFLOPS | Progress: (12/20) | 20.14 s
[Task 8/25] Current/Best: 18.00/ 18.34 GFLOPS | Progress: (16/20) | 22.20 s
[Task 8/25] Current/Best: 6.99/ 18.34 GFLOPS | Progress: (20/20) | 28.07 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 17.31/ 18.98 GFLOPS | Progress: (4/20) | 4.12 s
[Task 9/25] Current/Best: 13.12/ 20.37 GFLOPS | Progress: (8/20) | 7.67 s
[Task 9/25] Current/Best: 9.09/ 20.37 GFLOPS | Progress: (12/20) | 13.09 s
[Task 9/25] Current/Best: 13.75/ 20.37 GFLOPS | Progress: (16/20) | 15.04 s
[Task 9/25] Current/Best: 15.14/ 20.37 GFLOPS | Progress: (20/20) | 22.91 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 13.89/ 13.89 GFLOPS | Progress: (4/20) | 4.14 s
[Task 10/25] Current/Best: 9.49/ 16.16 GFLOPS | Progress: (8/20) | 5.82 s
[Task 10/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (12/20) | 7.54 s
[Task 10/25] Current/Best: 10.21/ 20.66 GFLOPS | Progress: (16/20) | 9.61 s
[Task 10/25] Current/Best: 10.56/ 20.66 GFLOPS | Progress: (20/20) | 12.17 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 21.30/ 21.30 GFLOPS | Progress: (4/20) | 4.28 s
[Task 11/25] Current/Best: 9.81/ 21.30 GFLOPS | Progress: (8/20) | 6.55 s
[Task 11/25] Current/Best: 13.39/ 21.30 GFLOPS | Progress: (12/20) | 8.99 s
[Task 11/25] Current/Best: 7.08/ 21.30 GFLOPS | Progress: (16/20) | 11.95 s
[Task 11/25] Current/Best: 15.47/ 21.30 GFLOPS | Progress: (20/20) | 14.49 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 14.32/ 14.93 GFLOPS | Progress: (4/20) | 4.92 s
[Task 12/25] Current/Best: 11.28/ 14.93 GFLOPS | Progress: (8/20) | 9.30 s
[Task 12/25] Current/Best: 10.70/ 14.93 GFLOPS | Progress: (12/20) | 11.85 s
[Task 12/25] Current/Best: 14.53/ 20.88 GFLOPS | Progress: (16/20) | 14.46 s
[Task 12/25] Current/Best: 4.39/ 20.88 GFLOPS | Progress: (20/20) | 17.35 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 11.75/ 18.52 GFLOPS | Progress: (4/20) | 4.17 s
[Task 13/25] Current/Best: 6.14/ 18.52 GFLOPS | Progress: (8/20) | 8.05 s
[Task 13/25] Current/Best: 17.59/ 18.52 GFLOPS | Progress: (12/20) | 12.08 s
[Task 13/25] Current/Best: 11.79/ 20.10 GFLOPS | Progress: (16/20) | 14.56 s
[Task 13/25] Current/Best: 3.11/ 20.10 GFLOPS | Progress: (20/20) | 18.07 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 16.94/ 16.94 GFLOPS | Progress: (4/20) | 3.25 s
[Task 14/25] Current/Best: 5.09/ 19.91 GFLOPS | Progress: (8/20) | 6.50 s
[Task 14/25] Current/Best: 9.42/ 19.91 GFLOPS | Progress: (12/20) | 15.48 s
[Task 14/25] Current/Best: 13.57/ 19.91 GFLOPS | Progress: (16/20) | 22.77 s
[Task 14/25] Current/Best: 13.71/ 19.91 GFLOPS | Progress: (20/20) | 26.67 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.87/ 16.87 GFLOPS | Progress: (4/20) | 7.48 s
[Task 15/25] Current/Best: 16.89/ 16.89 GFLOPS | Progress: (8/20) | 10.07 s
[Task 15/25] Current/Best: 12.91/ 17.92 GFLOPS | Progress: (12/20) | 11.76 s Done.
-
[Task 15/25] Current/Best: 14.06/ 17.92 GFLOPS | Progress: (16/20) | 14.88 s
[Task 15/25] Current/Best: 23.16/ 23.16 GFLOPS | Progress: (20/20) | 16.38 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 4.82/ 18.35 GFLOPS | Progress: (4/20) | 4.21 s
[Task 16/25] Current/Best: 10.27/ 18.35 GFLOPS | Progress: (8/20) | 6.49 s
[Task 16/25] Current/Best: 12.71/ 18.35 GFLOPS | Progress: (12/20) | 10.85 s
[Task 16/25] Current/Best: 6.42/ 18.35 GFLOPS | Progress: (16/20) | 13.28 s
[Task 16/25] Current/Best: 17.32/ 18.35 GFLOPS | Progress: (20/20) | 14.94 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 3.08/ 12.21 GFLOPS | Progress: (4/20) | 4.94 s
[Task 17/25] Current/Best: 13.13/ 17.71 GFLOPS | Progress: (8/20) | 8.13 s
[Task 17/25] Current/Best: 18.65/ 18.65 GFLOPS | Progress: (12/20) | 10.62 s
[Task 17/25] Current/Best: 14.54/ 18.65 GFLOPS | Progress: (16/20) | 13.38 s
[Task 17/25] Current/Best: 16.48/ 18.65 GFLOPS | Progress: (20/20) | 16.81 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.43/ 16.94 GFLOPS | Progress: (4/20) | 5.36 s
[Task 18/25] Current/Best: 12.03/ 16.94 GFLOPS | Progress: (8/20) | 9.01 s
[Task 18/25] Current/Best: 6.10/ 16.94 GFLOPS | Progress: (12/20) | 11.48 s
[Task 18/25] Current/Best: 10.12/ 16.97 GFLOPS | Progress: (16/20) | 14.94 s
[Task 18/25] Current/Best: 12.21/ 18.32 GFLOPS | Progress: (20/20) | 17.91 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 5.35/ 22.04 GFLOPS | Progress: (4/20) | 5.33 s
[Task 19/25] Current/Best: 9.79/ 22.04 GFLOPS | Progress: (8/20) | 8.55 s
[Task 19/25] Current/Best: 11.96/ 22.04 GFLOPS | Progress: (12/20) | 12.80 s
[Task 19/25] Current/Best: 8.81/ 22.04 GFLOPS | Progress: (16/20) | 15.80 s
[Task 19/25] Current/Best: 7.46/ 22.04 GFLOPS | Progress: (20/20) | 19.37 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.59/ 18.29 GFLOPS | Progress: (4/20) | 4.86 s
[Task 20/25] Current/Best: 7.11/ 18.29 GFLOPS | Progress: (8/20) | 9.40 s
[Task 20/25] Current/Best: 6.81/ 18.29 GFLOPS | Progress: (12/20) | 11.99 s
[Task 20/25] Current/Best: 16.89/ 18.29 GFLOPS | Progress: (16/20) | 14.70 s
[Task 20/25] Current/Best: 14.01/ 18.29 GFLOPS | Progress: (20/20) | 17.72 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 18.84/ 18.84 GFLOPS | Progress: (4/20) | 4.26 s
[Task 21/25] Current/Best: 8.96/ 18.84 GFLOPS | Progress: (8/20) | 5.78 s
[Task 21/25] Current/Best: 2.72/ 18.84 GFLOPS | Progress: (12/20) | 13.56 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 4.27/ 15.23 GFLOPS | Progress: (4/20) | 9.22 s
[Task 1/25] Current/Best: 22.56/ 22.56 GFLOPS | Progress: (8/20) | 12.15 s
[Task 1/25] Current/Best: 12.68/ 22.56 GFLOPS | Progress: (12/20) | 18.40 s
[Task 1/25] Current/Best: 6.08/ 22.56 GFLOPS | Progress: (16/20) | 20.88 s
[Task 1/25] Current/Best: 8.98/ 22.56 GFLOPS | Progress: (20/20) | 24.44 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 15.23/ 15.23 GFLOPS | Progress: (4/20) | 3.53 s
[Task 2/25] Current/Best: 16.97/ 19.37 GFLOPS | Progress: (8/20) | 4.94 s
[Task 2/25] Current/Best: 9.78/ 19.37 GFLOPS | Progress: (12/20) | 6.80 s
[Task 2/25] Current/Best: 18.50/ 19.58 GFLOPS | Progress: (16/20) | 8.74 s
[Task 2/25] Current/Best: 7.74/ 19.85 GFLOPS | Progress: (20/20) | 10.81 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 13.17/ 19.26 GFLOPS | Progress: (4/20) | 3.89 s
[Task 3/25] Current/Best: 19.11/ 20.00 GFLOPS | Progress: (8/20) | 6.03 s
[Task 3/25] Current/Best: 9.24/ 20.00 GFLOPS | Progress: (12/20) | 9.95 s
[Task 3/25] Current/Best: 12.87/ 20.00 GFLOPS | Progress: (16/20) | 12.69 s
[Task 3/25] Current/Best: 16.98/ 21.75 GFLOPS | Progress: (20/20) | 14.77 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 5.19/ 19.85 GFLOPS | Progress: (4/20) | 4.17 s
[Task 4/25] Current/Best: 15.63/ 19.85 GFLOPS | Progress: (8/20) | 8.71 s
[Task 4/25] Current/Best: 12.37/ 19.85 GFLOPS | Progress: (12/20) | 11.14 s
[Task 4/25] Current/Best: 16.38/ 19.85 GFLOPS | Progress: (16/20) | 12.94 s
[Task 4/25] Current/Best: 19.80/ 19.85 GFLOPS | Progress: (20/20) | 14.43 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 22.50/ 22.50 GFLOPS | Progress: (4/20) | 3.95 s
[Task 5/25] Current/Best: 16.33/ 22.50 GFLOPS | Progress: (8/20) | 6.33 s
[Task 5/25] Current/Best: 12.03/ 22.50 GFLOPS | Progress: (12/20) | 9.83 s
[Task 5/25] Current/Best: 12.40/ 22.50 GFLOPS | Progress: (16/20) | 11.82 s
[Task 5/25] Current/Best: 17.06/ 22.50 GFLOPS | Progress: (20/20) | 13.74 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 13.10/ 15.26 GFLOPS | Progress: (4/20) | 4.62 s
[Task 6/25] Current/Best: 3.72/ 15.26 GFLOPS | Progress: (8/20) | 8.09 s
[Task 6/25] Current/Best: 2.90/ 15.45 GFLOPS | Progress: (12/20) | 16.20 s
[Task 6/25] Current/Best: 2.62/ 15.45 GFLOPS | Progress: (16/20) | 19.95 s
[Task 6/25] Current/Best: 5.76/ 15.45 GFLOPS | Progress: (20/20) | 24.56 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 18.07/ 21.63 GFLOPS | Progress: (4/20) | 3.93 s
[Task 7/25] Current/Best: 19.61/ 21.63 GFLOPS | Progress: (8/20) | 6.36 s
[Task 7/25] Current/Best: 15.27/ 21.63 GFLOPS | Progress: (12/20) | 10.01 s
[Task 7/25] Current/Best: 19.25/ 21.63 GFLOPS | Progress: (16/20) | 12.55 s
[Task 7/25] Current/Best: 15.44/ 21.63 GFLOPS | Progress: (20/20) | 14.86 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 13.99/ 13.99 GFLOPS | Progress: (4/20) | 7.20 s
[Task 8/25] Current/Best: 11.36/ 13.99 GFLOPS | Progress: (8/20) | 19.00 s
[Task 8/25] Current/Best: 9.32/ 13.99 GFLOPS | Progress: (12/20) | 28.01 s
[Task 8/25] Current/Best: 12.92/ 14.32 GFLOPS | Progress: (16/20) | 31.44 s
[Task 8/25] Current/Best: 14.42/ 14.42 GFLOPS | Progress: (20/20) | 34.09 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 10.72/ 21.23 GFLOPS | Progress: (4/20) | 4.49 s
[Task 9/25] Current/Best: 11.52/ 21.23 GFLOPS | Progress: (8/20) | 7.21 s
[Task 9/25] Current/Best: 11.32/ 21.23 GFLOPS | Progress: (12/20) | 10.40 s
[Task 9/25] Current/Best: 10.15/ 21.23 GFLOPS | Progress: (16/20) | 13.38 s
[Task 9/25] Current/Best: 21.39/ 21.39 GFLOPS | Progress: (20/2
0) | 19.26 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 9.11/ 20.57 GFLOPS | Progress: (4/20) | 3.59 s
[Task 10/25] Current/Best: 11.82/ 20.57 GFLOPS | Progress: (8/20) | 5.92 s
[Task 10/25] Current/Best: 9.54/ 20.57 GFLOPS | Progress: (12/20) | 7.66 s
[Task 10/25] Current/Best: 18.41/ 20.57 GFLOPS | Progress: (16/20) | 9.94 s
[Task 10/25] Current/Best: 15.59/ 20.57 GFLOPS | Progress: (20/20) | 11.71 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.86/ 16.90 GFLOPS | Progress: (4/20) | 3.90 s
[Task 11/25] Current/Best: 10.00/ 22.05 GFLOPS | Progress: (8/20) | 6.21 s
[Task 11/25] Current/Best: 20.18/ 22.05 GFLOPS | Progress: (12/20) | 8.56 s
[Task 11/25] Current/Best: 23.20/ 23.20 GFLOPS | Progress: (16/20) | 11.21 s
[Task 11/25] Current/Best: 9.29/ 23.20 GFLOPS | Progress: (20/20) | 13.42 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 3.48/ 12.17 GFLOPS | Progress: (4/20) | 6.21 s
[Task 12/25] Current/Best: 8.11/ 16.26 GFLOPS | Progress: (8/20) | 8.65 s
[Task 12/25] Current/Best: 19.55/ 19.55 GFLOPS | Progress: (12/20) | 11.03 s
[Task 12/25] Current/Best: 12.76/ 19.55 GFLOPS | Progress: (16/20) | 15.24 s
[Task 12/25] Current/Best: 17.53/ 19.55 GFLOPS | Progress: (20/20) | 18.83 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.04/ 14.74 GFLOPS | Progress: (4/20) | 4.85 s
[Task 13/25] Current/Best: 14.34/ 18.23 GFLOPS | Progress: (8/20) | 7.05 s
[Task 13/25] Current/Best: 6.09/ 21.58 GFLOPS | Progress: (12/20) | 10.06 s
[Task 13/25] Current/Best: 8.29/ 21.58 GFLOPS | Progress: (16/20) | 13.98 s
[Task 13/25] Current/Best: 12.58/ 21.58 GFLOPS | Progress: (20/20) | 17.02 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 2.45/ 10.90 GFLOPS | Progress: (4/20) | 5.24 s
[Task 14/25] Current/Best: 9.30/ 17.68 GFLOPS | Progress: (8/20) | 9.91 s
[Task 14/25] Current/Best: 12.88/ 17.68 GFLOPS | Progress: (12/20) | 13.41 s
[Task 14/25] Current/Best: 21.08/ 21.08 GFLOPS | Progress: (16/20) | 18.08 s
[Task 14/25] Current/Best: 16.73/ 21.08 GFLOPS | Progress: (20/20) | 19.71 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 21/25] Current/Best: 16.28/ 20.81 GFLOPS | Progress: (16/20) | 16.00 s
[Task 21/25] Current/Best: 14.13/ 20.81 GFLOPS | Progress: (20/20) | 17.65 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 8.00/ 20.80 GFLOPS | Progress: (4/20) | 4.85 s
[Task 22/25] Current/Best: 9.72/ 22.91 GFLOPS | Progress: (8/20) | 6.52 s
[Task 22/25] Current/Best: 6.26/ 22.91 GFLOPS | Progress: (12/20) | 10.96 s
[Task 22/25] Current/Best: 9.44/ 22.91 GFLOPS | Progress: (16/20) | 13.05 s
[Task 22/25] Current/Best: 10.13/ 22.91 GFLOPS | Progress: (20/20) | 15.45 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 9.97/ 22.61 GFLOPS | Progress: (4/20) | 4.17 s
[Task 23/25] Current/Best: 12.23/ 22.61 GFLOPS | Progress: (8/20) | 6.92 s
[Task 23/25] Current/Best: 7.83/ 22.61 GFLOPS | Progress: (12/20) | 10.13 s
[Task 23/25] Current/Best: 21.39/ 22.92 GFLOPS | Progress: (16/20) | 12.96 s
[Task 23/25] Current/Best: 10.62/ 22.92 GFLOPS | Progress: (20/20) | 15.91 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 9.14/ 9.48 GFLOPS | Progress: (4/20) | 9.97 s
[Task 24/25] Current/Best: 3.35/ 9.48 GFLOPS | Progress: (8/20) | 20.65 s
[Task 24/25] Current/Best: 8.86/ 9.48 GFLOPS | Progress: (12/20) | 32.50 s
[Task 24/25] Current/Best: 2.81/ 9.48 GFLOPS | Progress: (16/20) | 43.45 s
[Task 24/25] Current/Best: 3.59/ 9.48 GFLOPS | Progress: (20/20) | 54.98 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 25/25] Current/Best: 5.74/ 5.74 GFLOPS | Progress: (4/20) | 4.29 s
[Task 25/25] Current/Best: 3.65/ 5.74 GFLOPS | Progress: (8/20) | 9.90 s
[Task 25/25] Current/Best: 3.01/ 9.40 GFLOPS | Progress: (12/20) | 14.90 s
[Task 25/25] Current/Best: 1.55/ 9.40 GFLOPS | Progress: (16/20) | 25.86 s
[Task 25/25] Current/Best: 3.45/ 9.40 GFLOPS | Progress: (20/20) | 37.35 s
+
[Task 15/25] Current/Best: 16.41/ 16.41 GFLOPS | Progress: (4/20) | 4.54 s
[Task 15/25] Current/Best: 9.49/ 16.41 GFLOPS | Progress: (8/20) | 8.61 s
[Task 15/25] Current/Best: 6.19/ 20.03 GFLOPS | Progress: (12/20) | 10.43 s
[Task 15/25] Current/Best: 10.53/ 22.37 GFLOPS | Progress: (16/20) | 15.23 s
[Task 15/25] Current/Best: 9.28/ 22.37 GFLOPS | Progress: (20/20) | 19.52 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 15.78/ 21.30 GFLOPS | Progress: (4/20) | 3.30 s
[Task 16/25] Current/Best: 12.07/ 21.30 GFLOPS | Progress: (8/20) | 6.97 s
[Task 16/25] Current/Best: 7.58/ 21.30 GFLOPS | Progress: (12/20) | 10.36 s
[Task 16/25] Current/Best: 20.52/ 21.30 GFLOPS | Progress: (16/20) | 13.73 s
[Task 16/25] Current/Best: 18.51/ 21.30 GFLOPS | Progress: (20/20) | 15.31 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.34/ 22.57 GFLOPS | Progress: (4/20) | 3.90 s
[Task 17/25] Current/Best: 11.87/ 22.57 GFLOPS | Progress: (8/20) | 7.23 s
[Task 17/25] Current/Best: 6.17/ 22.57 GFLOPS | Progress: (12/20) | 11.00 s
[Task 17/25] Current/Best: 17.40/ 22.57 GFLOPS | Progress: (16/20) | 13.32 s
[Task 17/25] Current/Best: 7.70/ 22.57 GFLOPS | Progress: (20/20) | 16.38 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 15.29/ 15.95 GFLOPS | Progress: (4/20) | 4.23 s
[Task 18/25] Current/Best: 20.44/ 20.44 GFLOPS | Progress: (8/20) | 6.45 s
[Task 18/25] Current/Best: 10.66/ 20.44 GFLOPS | Progress: (12/20) | 10.36 s
[Task 18/25] Current/Best: 9.59/ 20.44 GFLOPS | Progress: (16/20) | 13.94 s
[Task 18/25] Current/Best: 16.98/ 20.44 GFLOPS | Progress: (20/20) | 15.84 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 17.15/ 17.94 GFLOPS | Progress: (4/20) | 5.33 s
[Task 19/25] Current/Best: 16.78/ 17.94 GFLOPS | Progress: (8/20) | 8.88 s
[Task 19/25] Current/Best: 6.29/ 18.45 GFLOPS | Progress: (12/20) | 12.60 s
[Task 19/25] Current/Best: 13.10/ 21.39 GFLOPS | Progress: (16/20) | 16.24 s
[Task 19/25] Current/Best: 11.29/ 22.46 GFLOPS | Progress: (20/20) | 19.52 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 15.87/ 18.90 GFLOPS | Progress: (4/20) | 4.24 s
[Task 20/25] Current/Best: 16.92/ 18.90 GFLOPS | Progress: (8/20) | 6.38 s
[Task 20/25] Current/Best: 13.30/ 18.90 GFLOPS | Progress: (12/20) | 9.43 s
[Task 20/25] Current/Best: 16.29/ 18.90 GFLOPS | Progress: (16/20) | 12.89 s
[Task 20/25] Current/Best: 18.46/ 18.90 GFLOPS | Progress: (20/20) | 15.30 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 7.33/ 9.77 GFLOPS | Progress: (4/20) | 4.11 s
[Task 21/25] Current/Best: 12.73/ 12.73 GFLOPS | Progress: (8/20) | 6.64 s
[Task 21/25] Current/Best: 17.92/ 21.26 GFLOPS | Progress: (12/20) | 8.87 s
[Task 21/25] Current/Best: 9.99/ 21.26 GFLOPS | Progress: (16/20) | 11.01 s Done.
+
[Task 21/25] Current/Best: 14.43/ 21.26 GFLOPS | Progress: (20/20) | 13.27 s Done.
+
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 5.21/ 13.66 GFLOPS | Progress: (4/20) | 4.08 s
[Task 22/25] Current/Best: 17.97/ 17.97 GFLOPS | Progress: (8/20) | 6.37 s
[Task 22/25] Current/Best: 18.50/ 18.50 GFLOPS | Progress: (12/20) | 8.32 s
[Task 22/25] Current/Best: 9.68/ 18.50 GFLOPS | Progress: (16/20) | 10.59 s
[Task 22/25] Current/Best: 4.45/ 18.50 GFLOPS | Progress: (20/20) | 13.06 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 2.67/ 18.67 GFLOPS | Progress: (4/20) | 4.69 s
[Task 23/25] Current/Best: 12.32/ 18.67 GFLOPS | Progress: (8/20) | 7.92 s
[Task 23/25] Current/Best: 19.65/ 19.65 GFLOPS | Progress: (12/20) | 13.04 s
[Task 23/25] Current/Best: 6.14/ 22.04 GFLOPS | Progress: (16/20) | 15.80 s
[Task 23/25] Current/Best: 4.87/ 22.04 GFLOPS | Progress: (20/20) | 19.23 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 3.50/ 3.50 GFLOPS | Progress: (4/20) | 12.15 s
[Task 24/25] Current/Best: 2.80/ 9.97 GFLOPS | Progress: (8/20) | 23.90 s
[Task 24/25] Current/Best: 2.36/ 9.97 GFLOPS | Progress: (12/20) | 26.81 s
[Task 24/25] Current/Best: 3.82/ 9.97 GFLOPS | Progress: (16/20) | 31.71 s
[Task 24/25] Current/Best: 5.50/ 9.97 GFLOPS | Progress: (20/20) | 42.66 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 7.39/ 7.69 GFLOPS | Progress: (4/20) | 3.88 s
[Task 25/25] Current/Best: 5.23/ 7.69 GFLOPS | Progress: (8/20) | 14.82 s
[Task 25/25] Current/Best: 4.06/ 7.69 GFLOPS | Progress: (12/20) | 25.75 s
[Task 25/25] Current/Best: 3.50/ 7.69 GFLOPS | Progress: (16/20) | 27.87 s
[Task 25/25] Current/Best: 8.54/ 8.54 GFLOPS | Progress: (20/20) | 38.79 s
@@ -665,8 +664,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -723,8 +722,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 427.9868124599989, 'median': 426.6517240999974, 'std': 3.5526446388610853}
- unoptimized: {'mean': 517.6232956799993, 'median': 517.659318699998, 'std': 1.5351246130381426}
+ optimized: {'mean': 411.6475026200351, 'median': 412.2672734001753, 'std': 3.0716165239000963}
+ unoptimized: {'mean': 514.1060797499813, 'median': 513.3606129998952, 'std': 2.953015519281599}
@@ -747,7 +746,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 12 minutes 9.178 seconds)
+ **Total running time of the script:** ( 11 minutes 38.791 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 3d527a15b5..054df7b66d 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
- 1.278e-07 secs/op
+ 1.288e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index fe8ef48332..0e508a64f9 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, 0x10952740)), stage(b, placeholder(b, 0xcd55990)), 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, 0x198303f0)), stage(b, placeholder(b, 0x20a42140)), 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 0e7acdf561..2f2bf5a11e 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,29 +5,29 @@
Computation times
=================
-**15:55.014** total execution time for **tutorial** files:
+**15:06.764** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 12:09.178 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 11:38.791 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:38.354 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:29.212 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.200 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.977 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:36.033 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:34.798 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:27.835 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.385 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.406 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.819 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.838 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.619 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.170 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.162 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.000 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.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 15193ebeca..7964581112 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -285,8 +285,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000008
+ Numpy running time: 0.000007
+ naive: 0.000007
@@ -498,10 +498,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.75676000102976e-06 1.0
- naive 7.841299999999999e-06 1.010898880326195
- parallel 6.945800000000001e-06 0.8954511934206938
- vector 2.4883400000000003e-05 3.207963118195815
+ numpy 7.2933599949465134e-06 1.0
+ naive 6.6998e-06 0.9186163859513606
+ parallel 6.995700000000001e-06 0.9591875356279194
+ vector 2.47294e-05 3.3906731625937456
@@ -922,7 +922,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018577
+ Numpy running time: 0.017826
@@ -980,7 +980,7 @@ optimizations.
.. code-block:: none
- none: 3.402429
+ none: 3.263024
@@ -1080,7 +1080,7 @@ schedule.
.. code-block:: none
- blocking: 0.313091
+ blocking: 0.298400
@@ -1164,7 +1164,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.343664
+ vectorization: 0.335828
@I.ir_module
class Module:
@T.prim_func
@@ -1230,7 +1230,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.117127
+ loop permutation: 0.116744
@I.ir_module
class Module:
@T.prim_func
@@ -1321,7 +1321,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108402
+ array packing: 0.109167
@I.ir_module
class Module:
@T.prim_func
@@ -1404,7 +1404,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111008
+ block caching: 0.110256
@I.ir_module
class Module:
@T.prim_func
@@ -1478,7 +1478,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.147413
+ parallelization: 0.146220
@I.ir_module
class Module:
@T.prim_func
@@ -1548,13 +1548,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4024285011 1.0
- blocking 0.31309147660000003 0.09202000174251362
- vectorization 0.34366443789999995 0.10100563106289927
- loop permutation 0.11712691290000002 0.0344245038101853
- array packing 0.10840182999999999 0.031860134596495955
- block caching 0.1110082867 0.03262619234000397
- parallelization 0.1474132279 0.04332588557036291
+ none 3.2630241653 1.0
+ blocking 0.2984000276 0.09144891747149085
+ vectorization 0.3358284045 0.10291937401852622
+ loop permutation 0.11674430870000001 0.03577794793599594
+ array packing 0.10916693 0.03345575284452828
+ block caching 0.1102562794 0.033789599406740256
+ parallelization 0.14622028609999999 0.04481127895249792
@@ -1594,11 +1594,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.200 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 9ff2dafd74..7256ec3a11 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-20b1b80f25177e4efa9d08eed8311ed6b3d60c53
+6c5be6fbd062a5cd431f09a1d87ac614cee73a39
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 8e6c7cd4fe..452b801542 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -585,7 +585,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.087 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.880 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_keras.html b/docs/how_to/compile_models/from_keras.html
index bddff91fed..0be99cafc4 100644
--- a/docs/how_to/compile_models/from_keras.html
+++ b/docs/how_to/compile_models/from_keras.html
@@ -506,7 +506,7 @@ Tensorflow is also required since it’s used as the default backend of keras.</
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Relay top-1 id: 285, class name: Egyptian cat
1/1 [==============================] - ETA: 0s
-1/1 [==============================] - 1s 1s/step
+1/1 [==============================] - 1s 880ms/step
Keras top-1 id: 285, class name: Egyptian cat
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 82cc08f8b4..218efd1a20 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -439,7 +439,7 @@
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip39cab67a-948c-410c-b02a-9c120b33651c 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.zip362a85cc-5fe7-4587-9c52-f98a850c7209 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 e6b99a6a90..62b4bfc7c1 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -449,13 +449,13 @@ Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdo
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 40.0MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 49.8MB/s]
- 47%|####6 | 19.5M/41.5M [00:00<00:00, 23.5MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 25.6MB/s]
- 77%|#######7 | 32.0M/41.5M [00:01<00:00, 34.3MB/s]
- 96%|#########6| 40.0M/41.5M [00:01<00:00, 43.1MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 37.4MB/s]
+ 19%|#9 | 7.99M/41.5M [00:00<00:00, 44.4MB/s]
+ 35%|###4 | 14.3M/41.5M [00:00<00:00, 53.6MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:00<00:00, 54.6MB/s]
+ 67%|######6 | 27.7M/41.5M [00:00<00:00, 52.9MB/s]
+ 82%|########2 | 34.1M/41.5M [00:00<00:00, 55.9MB/s]
+ 96%|#########6| 40.0M/41.5M [00:00<00:00, 55.6MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 54.8MB/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 c8ac7e8563..0990e7c658 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -432,10 +432,10 @@ 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]
- 34%|###3 | 15.0M/44.7M [00:00<00:00, 157MB/s]
- 67%|######7 | 30.0M/44.7M [00:00<00:00, 117MB/s]
- 93%|#########3| 41.7M/44.7M [00:00<00:00, 110MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 114MB/s]
+ 30%|### | 13.6M/44.7M [00:00<00:00, 142MB/s]
+ 65%|######4 | 28.9M/44.7M [00:00<00:00, 153MB/s]
+ 97%|#########7| 43.4M/44.7M [00:00<00:00, 118MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 119MB/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 c672796bc4..8dbe717fd1 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -649,7 +649,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.758 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.877 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 f35dd49a7c..331e9d2d9a 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:21.595</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:07.783</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,43 +349,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:21.758</p></td>
+<td><p>01:17.877</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>01:16.087</p></td>
+<td><p>01:14.880</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>00:52.066</p></td>
+<td><p>00:50.409</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:36.680</p></td>
+<td><p>00:33.733</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:30.902</p></td>
+<td><p>00:29.568</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:30.273</p></td>
+<td><p>00:29.300</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:26.591</p></td>
+<td><p>00:26.765</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>00:24.772</p></td>
+<td><p>00:23.543</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>00:19.853</p></td>
+<td><p>00:19.171</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>00:02.615</p></td>
+<td><p>00:02.536</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 ac106cdcd9..0ef815317a 100644
--- a/docs/how_to/deploy_models/deploy_model_on_adreno.html
+++ b/docs/how_to/deploy_models/deploy_model_on_adreno.html
@@ -920,10 +920,9 @@ Top5 predictions:
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 3346.9771 3346.6590 3350.4903 3344.4391 1.7793
+ 2685.0209 2684.0255 2688.4638 2683.0311 1.9015
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.768 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-model-on-adreno-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/2387d8448da213eb625e6b3d916327d4/deploy_model_on_adreno.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_model_on_adreno.py</span></code></a></p>
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 cdbad53fa8..7ca52b0c6f 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -662,7 +662,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.6146 16.4764 17.1486 16.2948 0.3198
+ 15.5922 15.5360 15.8489 15.4871 0.1193
</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 953e819c04..427d4a6e4c 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -454,22 +454,25 @@ 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]
- 5%|4 | 7.99M/170M [00:00<00:02, 79.8MB/s]
- 10%|9 | 16.8M/170M [00:00<00:02, 76.4MB/s]
- 14%|#4 | 24.1M/170M [00:00<00:02, 59.1MB/s]
- 19%|#8 | 32.0M/170M [00:00<00:02, 65.3MB/s]
- 28%|##8 | 48.1M/170M [00:00<00:01, 95.5MB/s]
- 34%|###4 | 58.0M/170M [00:00<00:01, 90.6MB/s]
- 40%|###9 | 67.4M/170M [00:00<00:01, 92.8MB/s]
- 46%|####5 | 77.8M/170M [00:00<00:00, 97.3MB/s]
- 51%|#####1 | 87.3M/170M [00:01<00:00, 94.8MB/s]
- 57%|#####6 | 96.5M/170M [00:01<00:00, 84.0MB/s]
- 62%|######1 | 105M/170M [00:01<00:00, 78.4MB/s]
- 70%|######9 | 118M/170M [00:01<00:00, 94.9MB/s]
- 75%|#######5 | 128M/170M [00:01<00:00, 93.1MB/s]
- 85%|########4 | 144M/170M [00:01<00:00, 104MB/s]
- 94%|#########4| 160M/170M [00:01<00:00, 107MB/s]
-100%|##########| 170M/170M [00:01<00:00, 93.5MB/s]
+ 5%|4 | 7.99M/170M [00:00<00:02, 64.5MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:02, 69.0MB/s]
+ 14%|#4 | 24.0M/170M [00:00<00:02, 71.5MB/s]
+ 19%|#8 | 32.0M/170M [00:00<00:01, 75.2MB/s]
+ 24%|##3 | 40.0M/170M [00:00<00:01, 71.0MB/s]
+ 28%|##8 | 48.0M/170M [00:00<00:01, 74.5MB/s]
+ 35%|###4 | 59.3M/170M [00:00<00:01, 87.9MB/s]
+ 41%|####1 | 70.0M/170M [00:00<00:01, 95.2MB/s]
+ 47%|####7 | 80.0M/170M [00:01<00:01, 90.9MB/s]
+ 52%|#####2 | 88.8M/170M [00:01<00:01, 62.6MB/s]
+ 57%|#####6 | 96.0M/170M [00:01<00:01, 64.9MB/s]
+ 62%|######1 | 104M/170M [00:01<00:00, 70.6MB/s]
+ 69%|######8 | 116M/170M [00:01<00:00, 84.3MB/s]
+ 74%|#######3 | 125M/170M [00:01<00:00, 59.1MB/s]
+ 78%|#######7 | 132M/170M [00:02<00:00, 57.3MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 64.4MB/s]
+ 89%|########9 | 152M/170M [00:02<00:00, 60.5MB/s]
+ 96%|#########5| 163M/170M [00:02<00:00, 71.2MB/s]
+100%|##########| 170M/170M [00:02<00:00, 71.5MB/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=& [...]
@@ -567,7 +570,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 28.890 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 22.255 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 103263990c..aed0837d28 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -495,8 +495,8 @@ training. Other models require a full post training calibration.</p>
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 59%|#####8 | 7.99M/13.6M [00:00<00:00, 53.3MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 79.0MB/s]
+ 59%|#####8 | 7.99M/13.6M [00:00<00:00, 50.9MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 53.9MB/s]
</pre></div>
</div>
</div>
@@ -587,7 +587,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3870 90.3335 91.4580 90.0791 0.2373
+ 90.1450 90.0606 94.1685 89.8995 0.4423
</pre></div>
</div>
<div class="admonition note">
@@ -626,7 +626,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.948 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.751 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 332dd81e2f..8c962ba314 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -580,7 +580,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.7224 119.5941 126.5624 118.7859 0.8033
+ 118.1641 118.2210 119.2519 117.1100 0.4611
</pre></div>
</div>
<div class="admonition note">
@@ -608,7 +608,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 27.495 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 36.709 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 2535b47708..1a75fa73ff 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -521,7 +521,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 37.716 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 42.416 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 66994277c0..443a8e4567 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -463,24 +463,24 @@ 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]
- 3%|2 | 3977/132723 [00:00<00:03, 39762.26KB/s]
- 8%|7 | 10187/132723 [00:00<00:02, 52898.27KB/s]
- 14%|#3 | 17918/132723 [00:00<00:01, 64040.15KB/s]
- 19%|#9 | 25691/132723 [00:00<00:01, 69441.97KB/s]
- 25%|##5 | 33518/132723 [00:00<00:01, 72618.09KB/s]
- 31%|###1 | 41336/132723 [00:00<00:01, 74499.47KB/s]
- 37%|###7 | 49119/132723 [00:00<00:01, 75586.38KB/s]
- 43%|####2 | 56958/132723 [00:00<00:00, 76472.50KB/s]
- 49%|####8 | 64805/132723 [00:00<00:00, 77094.01KB/s]
- 55%|#####4 | 72585/132723 [00:01<00:00, 77263.00KB/s]
- 61%|###### | 80376/132723 [00:01<00:00, 77457.77KB/s]
- 66%|######6 | 88181/132723 [00:01<00:00, 77635.69KB/s]
- 72%|#######2 | 95977/132723 [00:01<00:00, 77730.00KB/s]
- 78%|#######8 | 103817/132723 [00:01<00:00, 77930.27KB/s]
- 84%|########4 | 111617/132723 [00:01<00:00, 77948.17KB/s]
- 90%|########9 | 119412/132723 [00:01<00:00, 77758.10KB/s]
- 96%|#########5| 127199/132723 [00:01<00:00, 77783.08KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 74925.02KB/s]
+ 4%|4 | 5640/132723 [00:00<00:02, 56397.90KB/s]
+ 10%|9 | 12997/132723 [00:00<00:01, 66494.82KB/s]
+ 16%|#5 | 20598/132723 [00:00<00:01, 70834.49KB/s]
+ 21%|##1 | 28475/132723 [00:00<00:01, 73963.67KB/s]
+ 27%|##7 | 36366/132723 [00:00<00:01, 75715.09KB/s]
+ 33%|###3 | 44179/132723 [00:00<00:01, 76534.74KB/s]
+ 39%|###9 | 51985/132723 [00:00<00:01, 77030.29KB/s]
+ 45%|####5 | 59828/132723 [00:00<00:00, 77473.83KB/s]
+ 51%|##### | 67646/132723 [00:00<00:00, 77692.56KB/s]
+ 57%|#####6 | 75558/132723 [00:01<00:00, 78131.71KB/s]
+ 63%|######2 | 83372/132723 [00:01<00:00, 77757.85KB/s]
+ 69%|######8 | 91186/132723 [00:01<00:00, 77866.92KB/s]
+ 75%|#######4 | 99068/132723 [00:01<00:00, 78153.94KB/s]
+ 81%|######## | 106946/132723 [00:01<00:00, 78337.39KB/s]
+ 86%|########6 | 114780/132723 [00:01<00:00, 78271.51KB/s]
+ 92%|#########2| 122672/132723 [00:01<00:00, 78465.54KB/s]
+ 98%|#########8| 130574/132723 [00:01<00:00, 78630.60KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 76781.09KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -519,7 +519,7 @@ 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 34.247 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 25.637 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 d4567304d2..f89f95c1cc 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:01.394</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>14:45.499</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -349,39 +349,39 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>03:34.247</p></td>
+<td><p>03:25.637</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:28.890</p></td>
+<td><p>03:22.255</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:27.495</p></td>
+<td><p>02:36.709</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>01:37.716</p></td>
+<td><p>01:42.416</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>01:13.948</p></td>
+<td><p>01:11.751</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>01:03.768</p></td>
+<td><p>00:54.388</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:41.008</p></td>
+<td><p>00:39.185</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:27.437</p></td>
+<td><p>00:26.705</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:26.879</p></td>
+<td><p>00:26.447</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 1a6c425259..d6bccee16d 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -619,7 +619,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipef6b2f36-e7aa-42bb-a715-69b30a51e523 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.zipb9b11189-fcad-489c-b4dc-d59850bff597 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 f0e43e5e8e..42e61743d1 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:52.757</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:51.322</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:48.939</p></td>
+<td><p>00:47.694</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>00:02.713</p></td>
+<td><p>00:02.577</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>00:01.098</p></td>
+<td><p>00:01.044</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 09be435037..4fd56a7758 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -526,10 +526,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 18444us [18444us] (48.44%; 48.44%)
-FoldScaleAxis: 19634us [8us] (51.56%; 51.56%)
- FoldConstant: 19625us [1724us] (51.54%; 99.96%)
- InferType: 17901us [17901us] (47.01%; 91.21%)
+InferType: 17965us [17965us] (48.54%; 48.54%)
+FoldScaleAxis: 19042us [6us] (51.46%; 51.46%)
+ FoldConstant: 19035us [1705us] (51.44%; 99.97%)
+ InferType: 17330us [17330us] (46.83%; 91.04%)
</pre></div>
</div>
</div>
@@ -551,10 +551,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 18098us [18098us] (47.97%; 47.97%)
-FoldScaleAxis: 19626us [8us] (52.03%; 52.03%)
- FoldConstant: 19618us [1758us] (52.00%; 99.96%)
- InferType: 17860us [17860us] (47.34%; 91.04%)
+InferType: 17388us [17388us] (47.56%; 47.56%)
+FoldScaleAxis: 19173us [5us] (52.44%; 52.44%)
+ FoldConstant: 19168us [1688us] (52.43%; 99.98%)
+ InferType: 17481us [17481us] (47.81%; 91.20%)
</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 c983c9d9a5..1fe4f81a30 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -575,7 +575,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.186111 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.126304 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 83635ed838..baf11a2c2c 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -867,7 +867,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.831319 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.691885 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 6a842c018f..585da49595 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -472,8 +472,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019284
-Baseline: 3.462858
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019105
+Baseline: 3.258741
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -532,7 +532,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.305168
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.298000
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.338542
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332539
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -644,7 +644,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117760
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.114561
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -721,7 +721,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110228
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.108607
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111027
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111281
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -879,7 +879,7 @@ class Module:
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.148403
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146370
</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 0628404929..e87d48ab53 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.190</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.377</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.707</p></td>
+<td><p>00:31.833</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>00:01.429</p></td>
+<td><p>00:01.469</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>00:01.055</p></td>
+<td><p>00:01.076</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 93d588d065..0d5763b8b0 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>09:38.124</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>09:08.538</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -349,27 +349,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>05:42.968</p></td>
+<td><p>05:29.796</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>01:39.009</p></td>
+<td><p>01:37.055</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>01:05.952</p></td>
+<td><p>01:04.667</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>00:43.021</p></td>
+<td><p>00:30.964</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>00:14.250</p></td>
+<td><p>00:13.513</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>00:12.923</p></td>
+<td><p>00:12.544</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 0dd0111b2f..cc0639ac09 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
@@ -507,307 +507,481 @@ class Module:
bias_1 = T.match_buffer(bias, (1, 512, 1, 1))
compute_1 = T.match_buffer(compute, (1, 512, 7, 7))
blockIdx_x = T.env_thread("blockIdx.x")
- T.launch_thread(blockIdx_x, 16)
- conv2d_nchw = T.allocate([28], "float32", "local")
- pad_temp_shared = T.allocate([2016], "float32", "shared")
+ 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.env_thread("threadIdx.x")
- T.launch_thread(threadIdx_x, 56)
- conv2d_nchw_1 = T.buffer_decl((4,), data=conv2d_nchw, scope="local", align=8)
+ T.launch_thread(threadIdx_x, 64)
+ conv2d_nchw_1 = T.buffer_decl((14,), data=conv2d_nchw, scope="local", align=32)
conv2d_nchw_1[0] = T.float32(0)
- conv2d_nchw_1[2] = T.float32(0)
- conv2d_nchw_1[4] = T.float32(0)
- conv2d_nchw_1[6] = T.float32(0)
- conv2d_nchw_1[8] = T.float32(0)
- conv2d_nchw_1[10] = T.float32(0)
- conv2d_nchw_1[12] = T.float32(0)
- conv2d_nchw_1[14] = T.float32(0)
- conv2d_nchw_1[16] = T.float32(0)
- conv2d_nchw_1[18] = T.float32(0)
- conv2d_nchw_1[20] = T.float32(0)
- conv2d_nchw_1[22] = T.float32(0)
- conv2d_nchw_1[24] = T.float32(0)
- conv2d_nchw_1[26] = T.float32(0)
conv2d_nchw_1[1] = T.float32(0)
+ conv2d_nchw_1[2] = T.float32(0)
conv2d_nchw_1[3] = T.float32(0)
+ conv2d_nchw_1[4] = T.float32(0)
conv2d_nchw_1[5] = T.float32(0)
+ conv2d_nchw_1[6] = T.float32(0)
conv2d_nchw_1[7] = T.float32(0)
+ conv2d_nchw_1[8] = T.float32(0)
conv2d_nchw_1[9] = T.float32(0)
+ conv2d_nchw_1[10] = T.float32(0)
conv2d_nchw_1[11] = T.float32(0)
+ conv2d_nchw_1[12] = T.float32(0)
conv2d_nchw_1[13] = T.float32(0)
- conv2d_nchw_1[15] = T.float32(0)
- conv2d_nchw_1[17] = T.float32(0)
- conv2d_nchw_1[19] = T.float32(0)
- conv2d_nchw_1[21] = T.float32(0)
- conv2d_nchw_1[23] = T.float32(0)
- conv2d_nchw_1[25] = T.float32(0)
- conv2d_nchw_1[27] = T.float32(0)
- for rc_outer_outer, ry_outer_outer in T.grid(16, 3):
- cse_var_4: T.int32 = rc_outer_outer * 1568
- cse_var_3: T.int32 = rc_outer_outer * 288
- cse_var_2: T.int32 = ry_outer_outer * 7
+ 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
threadIdx_x_1 = T.env_thread("threadIdx.x")
- pad_temp_shared_1 = T.buffer_decl((2016,), data=pad_temp_shared, scope="shared")
- data_2 = T.buffer_decl((25088,), data=data_1.data)
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 < threadIdx_x_1 * 6 % 9 and threadIdx_x_1 * 6 % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + threadIdx_x_1 * 6 % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 1) % 9 and (threadIdx_x_1 * 6 + 1) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 1) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 2] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 2) % 9 and (threadIdx_x_1 * 6 + 2) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 2) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 3] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 3) % 9 and (threadIdx_x_1 * 6 + 3) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 4] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 4) % 9 and (threadIdx_x_1 * 6 + 4) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 5] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 5) % 9 and (threadIdx_x_1 * 6 + 5) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 1) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 5) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 336] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 3) % 9 and (threadIdx_x_1 * 6 + 3) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 112) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 337] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 4) % 9 and (threadIdx_x_1 * 6 + 4) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 112) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 338] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 5) % 9 and (threadIdx_x_1 * 6 + 5) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 112) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 5) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 339] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 6) % 9 and (threadIdx_x_1 * 6 + 6) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 113) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 340] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 7) % 9 and (threadIdx_x_1 * 6 + 7) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 113) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 341] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 8) % 9 and (threadIdx_x_1 * 6 + 8) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 113) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 672] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 6) % 9 and (threadIdx_x_1 * 6 + 6) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 224) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 673] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 7) % 9 and (threadIdx_x_1 * 6 + 7) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 224) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 674] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 8) % 9 and (threadIdx_x_1 * 6 + 8) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 224) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 8) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 675] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 < threadIdx_x_1 * 6 % 9 and threadIdx_x_1 * 6 % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + threadIdx_x_1 * 6 % 9 + 517], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 676] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 <= (threadIdx_x_1 * 6 + 1) % 9 and (threadIdx_x_1 * 6 + 1) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 1) % 9 + 517], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 677] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 < (threadIdx_x_1 * 6 + 2) % 9 and (threadIdx_x_1 * 6 + 2) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 2) % 9 + 517], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1008] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 < threadIdx_x_1 * 6 % 9 and threadIdx_x_1 * 6 % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + threadIdx_x_1 * 6 % 9 + 776], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1009] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 1) % 9 and (threadIdx_x_1 * 6 + 1) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 1) % 9 + 776], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1010] = T.if_then_else(1 <= threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer and threadIdx_x_1 * 2 % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 2) % 9 and (threadIdx_x_1 * 6 + 2) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 2) % 9 + 776], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1011] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 3) % 9 and (threadIdx_x_1 * 6 + 3) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 337) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1012] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 4) % 9 and (threadIdx_x_1 * 6 + 4) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 337) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1013] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 1) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 5) % 9 and (threadIdx_x_1 * 6 + 5) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 337) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 5) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1344] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 3) % 9 and (threadIdx_x_1 * 6 + 3) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 448) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 3) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1345] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 4) % 9 and (threadIdx_x_1 * 6 + 4) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 448) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 4) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1346] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 7) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 5) % 9 and (threadIdx_x_1 * 6 + 5) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 448) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 5) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1347] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 6) % 9 and (threadIdx_x_1 * 6 + 6) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 449) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1348] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 7) % 9 and (threadIdx_x_1 * 6 + 7) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 449) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1349] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 8) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 8) % 9 and (threadIdx_x_1 * 6 + 8) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 449) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 8) % 9 - 8], T.float32(0))
- with T.launch_thread(threadIdx_x_1, 56):
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1680] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 6) % 9 and (threadIdx_x_1 * 6 + 6) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 560) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 6) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1681] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 <= (threadIdx_x_1 * 6 + 7) % 9 and (threadIdx_x_1 * 6 + 7) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 560) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 7) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1682] = T.if_then_else(1 <= (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer and (threadIdx_x_1 * 2 + 14) % 21 // 3 + ry_outer_outer < 8 and 1 < (threadIdx_x_1 * 6 + 8) % 9 and (threadIdx_x_1 * 6 + 8) % 9 < 8, data_2[cse_var_4 + (threadIdx_x_1 * 2 + 560) // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 8) % 9 - 8], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1683] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 < threadIdx_x_1 * 6 % 9 and threadIdx_x_1 * 6 % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + threadIdx_x_1 * 6 % 9 + 1301], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1684] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 <= (threadIdx_x_1 * 6 + 1) % 9 and (threadIdx_x_1 * 6 + 1) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 1) % 9 + 1301], T.float32(0))
- pad_temp_shared_1[threadIdx_x_1 * 6 + 1685] = T.if_then_else(1 <= ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 and ry_outer_outer + (threadIdx_x_1 * 2 // 3 + 5) % 7 < 8 and 1 < (threadIdx_x_1 * 6 + 2) % 9 and (threadIdx_x_1 * 6 + 2) % 9 < 8, data_2[cse_var_4 + threadIdx_x_1 * 2 // 3 * 7 + cse_var_2 + (threadIdx_x_1 * 6 + 2) % 9 + 1301], T.float32(0))
+ pad_temp_shared_1 = T.buffer_decl((72,), data=pad_temp_shared, scope="shared")
+ with T.launch_thread(threadIdx_x_1, 64):
+ data_2 = T.buffer_decl((25088,), data=data_1.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_2[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_2[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_2[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_2[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_2 = T.env_thread("threadIdx.x")
kernel_shared_1 = T.buffer_decl((3072,), data=kernel_shared, scope="shared")
kernel_2 = T.buffer_decl((2359296,), data=kernel_1.data)
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 56] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 56) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 112] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 112) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 168] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 168) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 224] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 224) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 280] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 280) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 336] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 336) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 392] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 392) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 448] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 448) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 504] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 504) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 8) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 560] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 560) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 616] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 616) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 40) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 672] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 32256]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 728] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 728) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 784] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 784) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 840] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 840) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 896] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 896) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 952] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 952) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1008] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1008) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1064] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1064) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1120] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1120) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1176] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1176) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 8) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1232] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1232) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1288] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1288) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 40) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1344] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 64512]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1400] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1400) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1456] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1456) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1512] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1512) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1568] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1568) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1624] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1624) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1680] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1680) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1736] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1736) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1792] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1792) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1848] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1848) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 8) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1904] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1904) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 1960] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 1960) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 40) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2016] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 96768]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2072] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2072) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2128] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2128) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2184] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2184) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2240] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2240) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2296] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2296) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2352] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2352) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2408] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2408) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 8) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2464] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2464) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 64) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2520] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2520) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 8) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2576] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2576) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 80) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2632] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2632) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 40) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2688] = kernel_2[blockIdx_x * 147456 + cse_var_3 + threadIdx_x_2 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 129024]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2744] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2744) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 56) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2800] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2800) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 16) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2856] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2856) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 24) % 32 * 9 + cse_var_1 + threadIdx_x_2 % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2912] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2912) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 32) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- kernel_shared_1[threadIdx_x_2 + 2968] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 2968) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 + 88) % 96 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
- with T.launch_thread(threadIdx_x_2, 56):
- if T.likely(threadIdx_x_2 < 48):
- kernel_shared_1[threadIdx_x_2 + 3024] = kernel_2[blockIdx_x * 147456 + (threadIdx_x_2 + 3024) // 96 * 4608 + cse_var_3 + (threadIdx_x_2 // 3 + 16) * 9 + cse_var_1 + threadIdx_x_2 % 3]
- for rc_outer_inner in range(32):
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1536]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1537]
- conv2d_nchw_1[0] = conv2d_nchw_1[0] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[2] = conv2d_nchw_1[2] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[4] = conv2d_nchw_1[4] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[6] = conv2d_nchw_1[6] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[8] = conv2d_nchw_1[8] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[10] = conv2d_nchw_1[10] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[12] = conv2d_nchw_1[12] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 2]
- conv2d_nchw_1[14] = conv2d_nchw_1[14] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[16] = conv2d_nchw_1[16] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[18] = conv2d_nchw_1[18] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[20] = conv2d_nchw_1[20] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[22] = conv2d_nchw_1[22] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[24] = conv2d_nchw_1[24] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[26] = conv2d_nchw_1[26] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1538]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 96]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1632]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 97]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 1] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1633]
- conv2d_nchw_1[1] = conv2d_nchw_1[1] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[3] = conv2d_nchw_1[3] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[5] = conv2d_nchw_1[5] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[7] = conv2d_nchw_1[7] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[9] = conv2d_nchw_1[9] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[11] = conv2d_nchw_1[11] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[13] = conv2d_nchw_1[13] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 98]
- conv2d_nchw_1[15] = conv2d_nchw_1[15] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 2] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[17] = conv2d_nchw_1[17] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 3] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[19] = conv2d_nchw_1[19] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 4] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[21] = conv2d_nchw_1[21] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 5] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[23] = conv2d_nchw_1[23] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 6] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[25] = conv2d_nchw_1[25] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 7] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- conv2d_nchw_1[27] = conv2d_nchw_1[27] + pad_temp_shared_1[rc_outer_inner * 63 + threadIdx_x % 7 * 9 + 8] * kernel_shared_1[threadIdx_x // 7 * 192 + rc_outer_inner * 3 + 1634]
- for i1_inner in range(2):
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 64] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 64) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 128] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 128) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 192] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 36864]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 256] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 256) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 320] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 320) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 384] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 73728]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 448] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 448) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 512] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 512) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 576] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 110592]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 640] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 640) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 704] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 704) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 768] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 147456]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 832] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 832) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 896] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 896) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 960] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 184320]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1024] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1024) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1088] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1088) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1152] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 221184]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1216] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1216) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1280] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1280) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1344] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 258048]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1408] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1408) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1472] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1472) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1536] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 294912]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1600] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1600) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1664] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1664) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1728] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 331776]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1792] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1792) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1856] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1856) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1920] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 368640]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 1984] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 1984) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2048] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2048) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2112] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 405504]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2176] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2176) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2240] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2240) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2304] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 442368]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2368] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2368) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2432] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2432) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2496] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 479232]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2560] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2560) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2624] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2624) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2688] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 516096]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2752] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2752) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2816] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2816) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 2) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2880] = kernel_2[blockIdx_x // 7 * 589824 + threadIdx_x_2 // 24 * 4608 + cse_var_2 + threadIdx_x_2 % 24 // 3 * 9 + cse_var_1 + threadIdx_x_2 % 3 + 552960]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 2944] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 2944) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 16) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 1) % 3]
+ with T.launch_thread(threadIdx_x_2, 64):
+ kernel_shared_1[threadIdx_x_2 + 3008] = kernel_2[blockIdx_x // 7 * 589824 + (threadIdx_x_2 + 3008) // 24 * 4608 + cse_var_2 + (threadIdx_x_2 + 8) % 24 // 3 * 9 + cse_var_1 + (threadIdx_x_2 + 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_2 = T.buffer_decl((25088,), data=compute_1.data)
bias_2 = T.buffer_decl((512,), data=bias_1.data)
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7] = T.max(conv2d_nchw_1[i1_inner] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 1] = T.max(conv2d_nchw_1[i1_inner + 2] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 2] = T.max(conv2d_nchw_1[i1_inner + 4] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 3] = T.max(conv2d_nchw_1[i1_inner + 6] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 4] = T.max(conv2d_nchw_1[i1_inner + 8] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 5] = T.max(conv2d_nchw_1[i1_inner + 10] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 6] = T.max(conv2d_nchw_1[i1_inner + 12] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 784] = T.max(conv2d_nchw_1[i1_inner + 14] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 785] = T.max(conv2d_nchw_1[i1_inner + 16] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 786] = T.max(conv2d_nchw_1[i1_inner + 18] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 787] = T.max(conv2d_nchw_1[i1_inner + 20] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 788] = T.max(conv2d_nchw_1[i1_inner + 22] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 789] = T.max(conv2d_nchw_1[i1_inner + 24] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
- compute_2[blockIdx_x * 1568 + threadIdx_x // 7 * 98 + i1_inner * 49 + threadIdx_x % 7 * 7 + 790] = T.max(conv2d_nchw_1[i1_inner + 26] + bias_2[blockIdx_x * 32 + threadIdx_x // 7 * 2 + i1_inner + 16], T.float32(0))
+ compute_2[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_2[blockIdx_x // 7 * 128 + threadIdx_x * 2 + i1_inner], T.float32(0))
</pre></div>
</div>
</div>
@@ -841,7 +1015,7 @@ 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: 0.315 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.354 ms
</pre></div>
</div>
</div>
@@ -872,35 +1046,35 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_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=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_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=7)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=32)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_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=8)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+compute_i1_o_o_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=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_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=7)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -919,14 +1093,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+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=6)
+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=56)
+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", 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -944,238 +1118,430 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[28];
- __shared__ float pad_temp_shared[2016];
+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[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
- conv2d_nchw[16] = 0.000000e+00f;
- conv2d_nchw[18] = 0.000000e+00f;
- conv2d_nchw[20] = 0.000000e+00f;
- conv2d_nchw[22] = 0.000000e+00f;
- conv2d_nchw[24] = 0.000000e+00f;
- conv2d_nchw[26] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- conv2d_nchw[17] = 0.000000e+00f;
- conv2d_nchw[19] = 0.000000e+00f;
- conv2d_nchw[21] = 0.000000e+00f;
- conv2d_nchw[23] = 0.000000e+00f;
- conv2d_nchw[25] = 0.000000e+00f;
- conv2d_nchw[27] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ 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();
- pad_temp_shared[(((int)threadIdx.x) * 6)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 2)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0.0000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0.0000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 336)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 112) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0. [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 337)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 112) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 338)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 112) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0. [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 339)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 113) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0. [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 340)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 113) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 341)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 113) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0. [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 672)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 224) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 673)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 224) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 674)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 224) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 675)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) + 517)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 676)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) + 517)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 677)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) + 517)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1008)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1009)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1010)] = (((((1 <= ((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) + 776)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1011)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 337) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1012)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 337) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1013)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 337) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1344)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 3) % 9))) && ((((((int)threadIdx.x) * 6) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 448) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 3) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1345)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 4) % 9))) && ((((((int)threadIdx.x) * 6) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 448) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 4) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1346)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 5) % 9))) && ((((((int)threadIdx.x) * 6) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 448) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 5) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1347)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 449) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1348)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 449) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1349)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 449) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1680)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 6) % 9))) && ((((((int)threadIdx.x) * 6) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 560) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 6) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1681)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 7) % 9))) && ((((((int)threadIdx.x) * 6) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 560) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 7) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1682)] = (((((1 <= (((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 2) + 14) % 21) / 3) + ry_outer_outer) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 8) % 9))) && ((((((int)threadIdx.x) * 6) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 2) + 560) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 8) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1683)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 < ((((int)threadIdx.x) * 6) % 9))) && (((((int)threadIdx.x) * 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 6) % 9)) + 1301)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1684)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 6) + 1) % 9))) && ((((((int)threadIdx.x) * 6) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 1) % 9)) + 1301)] : 0.00000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 6) + 1685)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 2) / 3) + 5) % 7)) < 8)) && (1 < (((((int)threadIdx.x) * 6) + 2) % 9))) && ((((((int)threadIdx.x) * 6) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 6) + 2) % 9)) + 1301)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1624)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1624) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1680)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1680) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1736)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1736) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1792) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1848)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1848) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 1904)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1904) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 2072)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2072) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2128)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2128) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2184)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2184) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2240) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2296)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2296) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2408)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2408) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 8) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2464) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2520)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2520) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 2576)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2576) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2632)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2632) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 40) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2800)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2800) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 16) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2856)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2856) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2912) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2968)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2968) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- if (((int)threadIdx.x) < 48) {
- kernel_shared[(((int)threadIdx.x) + 3024)] = kernel[(((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3024) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 144)];
+ 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);
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 32; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3))]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1536)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1537)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 2)]));
- conv2d_nchw[14] = (conv2d_nchw[14] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[16] = (conv2d_nchw[16] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[18] = (conv2d_nchw[18] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[20] = (conv2d_nchw[20] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[22] = (conv2d_nchw[22] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[24] = (conv2d_nchw[24] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[26] = (conv2d_nchw[26] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1538)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 96)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1632)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 97)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1633)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 98)]));
- conv2d_nchw[15] = (conv2d_nchw[15] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[17] = (conv2d_nchw[17] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[19] = (conv2d_nchw[19] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[21] = (conv2d_nchw[21] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[23] = (conv2d_nchw[23] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[25] = (conv2d_nchw[25] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
- conv2d_nchw[27] = (conv2d_nchw[27] + (pad_temp_shared[(((rc_outer_inner * 63) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + (rc_outer_inner * 3)) + 1634)]));
+ 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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)] = 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) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 784)] = max((conv2d_nchw[(i1_inner + 14)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 785)] = max((conv2d_nchw[(i1_inner + 16)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 786)] = max((conv2d_nchw[(i1_inner + 18)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 787)] = max((conv2d_nchw[(i1_inner + 20)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 788)] = max((conv2d_nchw[(i1_inner + 22)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 789)] = max((conv2d_nchw[(i1_inner + 24)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + 790)] = max((conv2d_nchw[(i1_inner + 26)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner) + 16)]), 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);
+ }
}
}
</pre></div>
@@ -1212,7 +1578,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 42.968 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 29.796 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 03eecdc001..73831d893f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -916,7 +916,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 7.8608 7.8596 7.8690 7.8538 0.0063
+ 7.8726 7.8762 7.8767 7.8649 0.0054
</pre></div>
</div>
</div>
@@ -938,7 +938,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.952 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.667 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 1b38efd522..deaad06b86 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -935,7 +935,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 763.9441 763.1073 767.3202 761.4047 2.4864
+ 744.6278 743.8504 746.7951 743.2380 1.5527
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 39.009 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 37.055 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 c3ff7ba21d..1b7cfa6094 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -736,7 +736,7 @@ 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: 1.728 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.716 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 1c02f8371b..8969c3368e 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:32.327</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:37.938</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,22 +349,22 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:32.294</p></td>
+<td><p>00:37.906</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.020</p></td>
+<td><p>00:00.018</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
<td><p>00:00.004</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></td>
<td><p>00:00.004</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 674913281f..9c4579de90 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -568,7 +568,8 @@ for this template</p>
waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+No: 1 GFLOPS: 111.35/111.35 result: MeasureResult(costs=(0.0020790124897959185,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7945833206176758, timestamp=1674022602.5026455) [('tile_f', [-1, 1, 32, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,979530
+No: 2 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -690,8 +691,8 @@ 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, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8611762
-No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,8198569
+No: 3 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -813,8 +814,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4044736
-No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2580687
+No: 4 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -936,8 +937,26 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,373192
-No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 16, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10439569
+No: 5 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
+ File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
+ res = future.result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
+ return self.__get_result()
+ File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
+ raise self._exception
+ File "/usr/lib/python3.7/concurrent/futures/thread.py", line 57, in run
+ result = self.fn(*self.args, **self.kwargs)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 432, in <lambda>
+ worker = lambda *args: self._worker_run(*args)
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 401, in _worker_run
+ return proc.recv()
+ File "/workspace/python/tvm/contrib/popen_pool.py", line 309, in recv
+ raise TimeoutError()
+TimeoutError
+
+ [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2949493
+No: 6 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1059,8 +1078,8 @@ 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, 64, 1, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4184726
-No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2547744
+No: 7 GFLOPS: 0.00/111.35 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 592, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 544, in _build_func_common
@@ -1182,8 +1201,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1713268
-No: 6 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 256, 1, 1]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,8904508
+No: 8 GFLOPS: 0.00/111.35 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
@@ -1305,8 +1324,8 @@ 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, 8, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1452744
-No: 7 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 64, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 128, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6608963
+No: 9 GFLOPS: 0.00/111.35 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
@@ -1428,9 +1447,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 512, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7466854
-No: 8 GFLOPS: 9.05/9.05 result: MeasureResult(costs=(0.025575887500000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4544157981872559, timestamp=1674000444.1167586) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,292278
-No: 9 GFLOPS: 0.00/9.05 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9258557
+No: 10 GFLOPS: 0.00/111.35 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
@@ -1552,8 +1570,8 @@ 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, 1, 7, 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', 0)],None,4678616
-No: 10 GFLOPS: 0.00/9.05 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9603335
+No: 11 GFLOPS: 0.00/111.35 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
@@ -1675,9 +1693,8 @@ 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, 8, 16]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7654200
-No: 11 GFLOPS: 37.37/37.37 result: MeasureResult(costs=(0.0061950823600000005,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.392481803894043, timestamp=1674000445.7371573) [('tile_f', [-1, 1, 8, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6497947
-No: 12 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2587768
+No: 12 GFLOPS: 0.00/111.35 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
@@ -1799,8 +1816,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4454169
-No: 13 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,736315
+No: 13 GFLOPS: 0.00/111.35 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
@@ -1922,8 +1939,8 @@ 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, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 256, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6840785
-No: 14 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10044555
+No: 14 GFLOPS: 0.00/111.35 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
@@ -2045,9 +2062,8 @@ 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, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2304695
-No: 15 GFLOPS: 1.62/37.37 result: MeasureResult(costs=(0.143244812,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.765275716781616, timestamp=1674000454.710923) [('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,1948741
-No: 16 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6348485
+No: 15 GFLOPS: 0.00/111.35 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
@@ -2169,8 +2185,8 @@ 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, 32, 2]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 1, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7841992
-No: 17 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7624397
+No: 16 GFLOPS: 0.00/111.35 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
@@ -2292,8 +2308,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3958997
-No: 18 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 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,4848126
+No: 17 GFLOPS: 0.00/111.35 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
@@ -2415,8 +2431,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 64, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3989510
-No: 19 GFLOPS: 0.00/37.37 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, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7195926
+No: 18 GFLOPS: 0.00/111.35 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
@@ -2538,8 +2554,8 @@ 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, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5790861
-No: 20 GFLOPS: 0.00/37.37 result: Traceback (most recent call last):
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2240121
+No: 19 GFLOPS: 0.00/111.35 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
@@ -2661,7 +2677,8 @@ Traceback (most recent call last):
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 875, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
-tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 128, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7774715
+tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 4, 4]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9268500
+No: 20 GFLOPS: 234.57/234.57 result: MeasureResult(costs=(0.0009869387213114753,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.453100681304932, timestamp=1674022621.5645502) [('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7851432
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2700,9 +2717,9 @@ 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 16, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6497947
+[('tile_f', [-1, 1, 4, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7851432
Finish loading 20 records
-Time cost of this operator: 0.006520
+Time cost of this operator: 0.001165
</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 3cc71996cc..be321e7fd7 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -646,10 +646,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.4 98.744 (1, 2, 10, 10, 3) 2 1 [315.4]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.021 0.946 (1, 6, 10, 10) 1 1 [3.021]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.99 0.31 (1, 1, 10, 10, 3) 1 1 [0.99]
-Total_time - 319.411 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.2 98.702 (1, 2, 10, 10, 3) 2 1 [308.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.09 0.99 (1, 6, 10, 10) 1 1 [3.09]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.965 0.309 (1, 1, 10, 10, 3) 1 1 [0.965]
+Total_time - 312.254 - - - - -
</pre></div>
</div>
</div>
@@ -701,10 +701,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 102.5 97.46 (1, 6, 10, 10, 1) 2 1 [102.5]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.805 1.716 (1, 6, 10, 10) 1 1 [1.805]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.867 0.824 (1, 3, 10, 10, 1) 1 1 [0.867]
-Total_time - 105.172 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 100.1 97.36 (1, 6, 10, 10, 1) 2 1 [100.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 1.703 (1, 6, 10, 10) 1 1 [1.75]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.964 0.938 (1, 1, 10, 10, 3) 1 1 [0.964]
+Total_time - 102.814 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_pytorch.html b/docs/how_to/work_with_microtvm/micro_pytorch.html
index 9504c27b9b..87b57cf915 100644
--- a/docs/how_to/work_with_microtvm/micro_pytorch.html
+++ b/docs/how_to/work_with_microtvm/micro_pytorch.html
@@ -453,7 +453,7 @@ download a cat image and preprocess it to use as the model input.</p>
Downloading: "https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2_qnnpack_37f702c5.pth
0%| | 0.00/3.42M [00:00<?, ?B/s]
-100%|##########| 3.42M/3.42M [00:00<00:00, 51.5MB/s]
+100%|##########| 3.42M/3.42M [00:00<00:00, 71.2MB/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.
@@ -577,7 +577,7 @@ 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 10.838 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.816 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 0dcff16048..6de6b75d46 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -523,7 +523,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp5iwbtdqy/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpdfofimzq/images/random'
</pre></div>
</div>
</div>
@@ -583,8 +583,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp5iwbtdqy/images/target contains 8144 images
-/tmp/tmp5iwbtdqy/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [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/tmpdfofimzq/images/target contains 8144 images
+/tmp/tmpdfofimzq/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -696,13 +696,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 47s - loss: 0.2298 - accuracy: 0.9200 - val_loss: 0.1528 - val_accuracy: 0.9551 - 47s/epoch - 145ms/step
+328/328 - 47s - loss: 0.2342 - accuracy: 0.9197 - val_loss: 0.1264 - val_accuracy: 0.9532 - 47s/epoch - 143ms/step
Epoch 2/3
-328/328 - 44s - loss: 0.1025 - accuracy: 0.9607 - val_loss: 0.1187 - val_accuracy: 0.9694 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.1031 - accuracy: 0.9623 - val_loss: 0.1160 - val_accuracy: 0.9532 - 43s/epoch - 131ms/step
Epoch 3/3
-328/328 - 44s - loss: 0.0705 - accuracy: 0.9750 - val_loss: 0.1366 - val_accuracy: 0.9619 - 44s/epoch - 133ms/step
+328/328 - 43s - loss: 0.0653 - accuracy: 0.9745 - val_loss: 0.1150 - val_accuracy: 0.9600 - 43s/epoch - 131ms/step
-<keras.callbacks.History object at 0x7f57f1b84410>
+<keras.callbacks.History object at 0x7f2087634f90>
</pre></div>
</div>
</div>
@@ -962,7 +962,7 @@ 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> ( 5 minutes 23.445 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 45.460 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 88b74f06f5..55868eb4ba 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>07:40.955</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:55.995</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,23 +349,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>05:23.445</p></td>
+<td><p>04:45.460</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_pytorch.html#sphx-glr-how-to-work-with-microtvm-micro-pytorch-py"><span class="std std-ref">microTVM PyTorch Tutorial</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_pytorch.py</span></code>)</p></td>
-<td><p>01:10.838</p></td>
+<td><p>01:07.816</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:53.689</p></td>
+<td><p>00:50.563</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:09.003</p></td>
+<td><p>00:08.439</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.980</p></td>
+<td><p>00:03.716</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">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 c2f9ccca52..d181ee15df 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.768</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.054</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,15 +349,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:32.755</p></td>
+<td><p>00:31.577</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.407</p></td>
+<td><p>00:09.963</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>00:01.601</p></td>
+<td><p>00:01.508</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index aec7c5dcdf..7c3b5cc9e4 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -535,7 +535,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f57f227d8c0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f2087e5d9e0>
</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 5e61dc0d7a..6fea058f8b 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:07.050</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.522</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,19 +349,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:04.483</p></td>
+<td><p>00:02.165</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>00:01.208</p></td>
+<td><p>00:01.088</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>00:00.579</p></td>
+<td><p>00:00.534</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>00:00.559</p></td>
+<td><p>00:00.515</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>
@@ -369,7 +369,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.050</p></td>
+<td><p>00:00.049</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
@@ -377,7 +377,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.024</p></td>
+<td><p>00:00.023</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 77b9ca3006..b018978aa0 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -586,7 +586,7 @@ class Module:
B_1 = T.match_buffer(B, (512, 64))
C_1 = T.match_buffer(C, (1024, 512))
i = T.var("int32")
- T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmp8mz2ijcq/input0.cc'\nsource_filename = \"/tmp/tmp8mz2ijcq/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca [...]
+ T.attr(T.iter_var(i, None, "DataPar", ""), "pragma_import_llvm", "; ModuleID = '/tmp/tmpa__vx31f/input0.cc'\nsource_filename = \"/tmp/tmpa__vx31f/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca [...]
for i, j_outer in T.grid(1024, 32):
T.call_extern("int32", "gemv_update", T.tvm_access_ptr(T.type_annotation("float32"), C_1.data, i * 512 + j_outer * 16, 16, 2), T.tvm_access_ptr(T.type_annotation("float32"), A_1.data, i * 64, 64, 1), T.tvm_access_ptr(T.type_annotation("float32"), B_1.data, j_outer * 1024, 1024, 1), 16, 64, 64)
</pre></div>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 29104dd18a..ca69db1d30 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1615,7 +1615,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
@@ -1899,7 +1899,7 @@ Candidates:
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index cb7363bd49..7dfedf736b 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/20b1b80f2/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 57754901e0..119d8583bd 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/20b1b80f2/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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 03b44d3b47..56ccecd1b5 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/20b1b80f2/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index c10d332956..5258f47229 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/20b1b80f2/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index 1f8a764f96..bb7bf4ba23 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/20b1b80f2/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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 77837b3c1b..ace4e6b8c4 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/20b1b80f2/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 75c081ec67..29a90a8dfa 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 1e3c2f4e3b..3c0de8032f 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index f2e9f98929..6a35afdc41 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/20b1b80f2/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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 96908868b0..9ccd14b101 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index e690e281c0..1a97231423 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/20b1b80f2/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index 8a5ec43a54..8f0956e8d7 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 2670bc5a23..1547deff00 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/20b1b80f2/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index d19c2cc8ac..66f2ea961f 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/20b1b80f2/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index b28b8d4405..3eb895f52b 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/20b1b80f2/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/webgpu.ts#L172">webgpu.ts:172</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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/20b1b80f2/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/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 588651f533..4e04ada7a5 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/20b1b80f2/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index ee3d53ea2d..0bbd15f37e 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/20b1b80f2/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 0ed6d536bc..88abc86176 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/20b1b80f2/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index b77e603556..46af907d62 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/20b1b80f2/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 6a74827bfe..901d5f0a87 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/20b1b80f2/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index c414bf8f61..98d055aeed 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L1367">runtime.ts:1367</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 9e04800a3d..d009b7e535 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index 4858ef4362..721268a3ac 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index 55a280cbd1..625a6062c1 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/20b1b80f2/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/6c5be6fbd/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 118e0ce215..03285c3f6d 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index ee8b0742bc..131d2fa3df 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:30.395</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:29.221</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -349,7 +349,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:30.388</p></td>
+<td><p>00:29.215</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 186d03c452..b4bdcdbd26 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -583,7 +583,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 32.78s!
+resnet18_v1 inference graph built in 31.10s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index bf78edb3eb..828fa10e25 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -601,7 +601,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 22.33s!
+yolov3-tiny inference graph built in 21.25s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 628545bf85..243dffccd8 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:39.096</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:35.883</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -348,12 +348,12 @@
<col style="width: 7%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:49.648</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
+<td><p>00:48.072</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:49.448</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
+<td><p>00:47.811</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index fe9af525ae..9ad7442bc8 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.150</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.075</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.679</p></td>
+<td><p>00:02.657</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.471</p></td>
+<td><p>00:00.418</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 796fa6b1a5..d854006b2c 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.833</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.777</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -349,11 +349,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.450</p></td>
+<td><p>00:00.427</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.383</p></td>
+<td><p>00:00.349</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index baa1e03ade..ce8dff280b 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -492,8 +492,7 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
-.T
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
</pre></div>
</div>
</div>
@@ -574,7 +573,7 @@ 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: 94.022 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.901 ms
</pre></div>
</div>
</div>
@@ -648,7 +647,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 38.354 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.212 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index bf6891070c..48ee8dfaa5 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -680,16 +680,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.12/10.12 result: MeasureResult(costs=(0.026523687400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6611154079437256, timestamp=1673998892.190876) [('tile_y', [-1, 512]), ('tile_x', [-1, 512])],None,99
-No: 2 GFLOPS: 9.29/10.12 result: MeasureResult(costs=(0.028901774400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7235610485076904, timestamp=1673998893.6952832) [('tile_y', [-1, 8]), ('tile_x', [-1, 32])],None,53
-No: 3 GFLOPS: 8.27/10.12 result: MeasureResult(costs=(0.0324548154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.7526891231536865, timestamp=1673998894.4671183) [('tile_y', [-1, 4]), ('tile_x', [-1, 32])],None,52
-No: 4 GFLOPS: 12.49/12.49 result: MeasureResult(costs=(0.0214984956,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5797519683837891, timestamp=1673998895.863199) [('tile_y', [-1, 32]), ('tile_x', [-1, 512])],None,95
-No: 5 GFLOPS: 11.64/12.49 result: MeasureResult(costs=(0.023065638399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6571595668792725, timestamp=1673998896.7626605) [('tile_y', [-1, 16]), ('tile_x', [-1, 256])],None,84
-No: 6 GFLOPS: 8.58/12.49 result: MeasureResult(costs=(0.031269829,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.9039361476898193, timestamp=1673998898.3122692) [('tile_y', [-1, 16]), ('tile_x', [-1, 64])],None,64
-No: 7 GFLOPS: 2.25/12.49 result: MeasureResult(costs=(0.11905661940000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1431119441986084, timestamp=1673998900.4692845) [('tile_y', [-1, 4]), ('tile_x', [-1, 2])],None,12
-No: 8 GFLOPS: 12.77/12.77 result: MeasureResult(costs=(0.0210180726,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5991122722625732, timestamp=1673998901.062802) [('tile_y', [-1, 64]), ('tile_x', [-1, 512])],None,96
-No: 9 GFLOPS: 0.89/12.77 result: MeasureResult(costs=(0.3003506016,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.006605863571167, timestamp=1673998906.194126) [('tile_y', [-1, 256]), ('tile_x', [-1, 2])],None,18
-No: 10 GFLOPS: 0.50/12.77 result: MeasureResult(costs=(0.5337017275999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=8.752919673919678, timestamp=1673998914.984868) [('tile_y', [-1, 64]), ('tile_x', [-1, 1])],None,6
+No: 1 GFLOPS: 2.42/2.42 result: MeasureResult(costs=(0.11078919699999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0058329105377197, timestamp=1674021106.6407683) [('tile_y', [-1, 2]), ('tile_x', [-1, 4])],None,21
+No: 2 GFLOPS: 12.39/12.39 result: MeasureResult(costs=(0.0216594874,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5815625190734863, timestamp=1674021107.9928033) [('tile_y', [-1, 2]), ('tile_x', [-1, 512])],None,91
+No: 3 GFLOPS: 1.79/12.39 result: MeasureResult(costs=(0.1502231728,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.643393039703369, timestamp=1674021111.4178398) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 4 GFLOPS: 2.03/12.39 result: MeasureResult(costs=(0.1321356942,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.333951711654663, timestamp=1674021113.7726407) [('tile_y', [-1, 256]), ('tile_x', [-1, 4])],None,28
+No: 5 GFLOPS: 10.96/12.39 result: MeasureResult(costs=(0.024493366199999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.619408369064331, timestamp=1674021114.6219072) [('tile_y', [-1, 1]), ('tile_x', [-1, 512])],None,90
+No: 6 GFLOPS: 3.27/12.39 result: MeasureResult(costs=(0.08203405239999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5492236614227295, timestamp=1674021116.1835446) [('tile_y', [-1, 32]), ('tile_x', [-1, 8])],None,35
+No: 7 GFLOPS: 12.80/12.80 result: MeasureResult(costs=(0.020977112399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6758532524108887, timestamp=1674021117.5373123) [('tile_y', [-1, 64]), ('tile_x', [-1, 128])],None,76
+No: 8 GFLOPS: 12.95/12.95 result: MeasureResult(costs=(0.020725559400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5682404041290283, timestamp=1674021118.123468) [('tile_y', [-1, 128]), ('tile_x', [-1, 512])],None,97
+No: 9 GFLOPS: 13.87/13.87 result: MeasureResult(costs=(0.019353842399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.534494161605835, timestamp=1674021118.773921) [('tile_y', [-1, 128]), ('tile_x', [-1, 64])],None,67
+No: 10 GFLOPS: 0.90/13.87 result: MeasureResult(costs=(0.2990334894,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.992733716964722, timestamp=1674021123.8084934) [('tile_y', [-1, 128]), ('tile_x', [-1, 2])],None,17
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 611e91d326..4b04ae359f 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -558,7 +558,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 517.6232956799993, 'median': 517.659318699998, 'std': 1.5351246130381426}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 514.1060797499813, 'median': 513.3606129998952, 'std': 2.953015519281599}
</pre></div>
</div>
</div>
@@ -710,179 +710,178 @@ depending on the specifics of the model and the target platform.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 11.79/ 16.28 GFLOPS | Progress: (4/20) | 7.91 s
-[Task 1/25] Current/Best: 22.54/ 23.10 GFLOPS | Progress: (8/20) | 12.50 s
-[Task 1/25] Current/Best: 12.61/ 23.10 GFLOPS | Progress: (12/20) | 16.99 s
-[Task 1/25] Current/Best: 22.76/ 23.10 GFLOPS | Progress: (16/20) | 20.39 s
-[Task 1/25] Current/Best: 3.42/ 23.10 GFLOPS | Progress: (20/20) | 23.62 s Done.
+[Task 1/25] Current/Best: 4.27/ 15.23 GFLOPS | Progress: (4/20) | 9.22 s
+[Task 1/25] Current/Best: 22.56/ 22.56 GFLOPS | Progress: (8/20) | 12.15 s
+[Task 1/25] Current/Best: 12.68/ 22.56 GFLOPS | Progress: (12/20) | 18.40 s
+[Task 1/25] Current/Best: 6.08/ 22.56 GFLOPS | Progress: (16/20) | 20.88 s
+[Task 1/25] Current/Best: 8.98/ 22.56 GFLOPS | Progress: (20/20) | 24.44 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.07/ 19.79 GFLOPS | Progress: (4/20) | 3.24 s
-[Task 2/25] Current/Best: 19.18/ 19.79 GFLOPS | Progress: (8/20) | 5.03 s
-[Task 2/25] Current/Best: 9.15/ 22.12 GFLOPS | Progress: (12/20) | 6.55 s
-[Task 2/25] Current/Best: 12.93/ 22.12 GFLOPS | Progress: (16/20) | 8.32 s
-[Task 2/25] Current/Best: 14.06/ 22.12 GFLOPS | Progress: (20/20) | 10.28 s Done.
+[Task 2/25] Current/Best: 15.23/ 15.23 GFLOPS | Progress: (4/20) | 3.53 s
+[Task 2/25] Current/Best: 16.97/ 19.37 GFLOPS | Progress: (8/20) | 4.94 s
+[Task 2/25] Current/Best: 9.78/ 19.37 GFLOPS | Progress: (12/20) | 6.80 s
+[Task 2/25] Current/Best: 18.50/ 19.58 GFLOPS | Progress: (16/20) | 8.74 s
+[Task 2/25] Current/Best: 7.74/ 19.85 GFLOPS | Progress: (20/20) | 10.81 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.63/ 11.01 GFLOPS | Progress: (4/20) | 7.09 s
-[Task 3/25] Current/Best: 6.39/ 18.27 GFLOPS | Progress: (8/20) | 9.74 s
-[Task 3/25] Current/Best: 6.21/ 22.38 GFLOPS | Progress: (12/20) | 11.88 s
-[Task 3/25] Current/Best: 22.74/ 22.74 GFLOPS | Progress: (16/20) | 14.23 s
-[Task 3/25] Current/Best: 19.38/ 22.74 GFLOPS | Progress: (20/20) | 16.54 s Done.
+[Task 3/25] Current/Best: 13.17/ 19.26 GFLOPS | Progress: (4/20) | 3.89 s
+[Task 3/25] Current/Best: 19.11/ 20.00 GFLOPS | Progress: (8/20) | 6.03 s
+[Task 3/25] Current/Best: 9.24/ 20.00 GFLOPS | Progress: (12/20) | 9.95 s
+[Task 3/25] Current/Best: 12.87/ 20.00 GFLOPS | Progress: (16/20) | 12.69 s
+[Task 3/25] Current/Best: 16.98/ 21.75 GFLOPS | Progress: (20/20) | 14.77 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 15.17/ 15.17 GFLOPS | Progress: (4/20) | 6.57 s
-[Task 4/25] Current/Best: 12.11/ 15.17 GFLOPS | Progress: (8/20) | 11.12 s
-[Task 4/25] Current/Best: 15.74/ 15.74 GFLOPS | Progress: (12/20) | 12.98 s
-[Task 4/25] Current/Best: 16.44/ 17.27 GFLOPS | Progress: (16/20) | 15.70 s
-[Task 4/25] Current/Best: 14.37/ 17.27 GFLOPS | Progress: (20/20) | 19.93 s Done.
+[Task 4/25] Current/Best: 5.19/ 19.85 GFLOPS | Progress: (4/20) | 4.17 s
+[Task 4/25] Current/Best: 15.63/ 19.85 GFLOPS | Progress: (8/20) | 8.71 s
+[Task 4/25] Current/Best: 12.37/ 19.85 GFLOPS | Progress: (12/20) | 11.14 s
+[Task 4/25] Current/Best: 16.38/ 19.85 GFLOPS | Progress: (16/20) | 12.94 s
+[Task 4/25] Current/Best: 19.80/ 19.85 GFLOPS | Progress: (20/20) | 14.43 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 11.74/ 14.43 GFLOPS | Progress: (4/20) | 3.68 s
-[Task 5/25] Current/Best: 15.84/ 15.84 GFLOPS | Progress: (8/20) | 5.70 s
-[Task 5/25] Current/Best: 12.14/ 21.83 GFLOPS | Progress: (12/20) | 7.73 s
-[Task 5/25] Current/Best: 6.25/ 21.83 GFLOPS | Progress: (16/20) | 10.50 s
-[Task 5/25] Current/Best: 9.02/ 21.83 GFLOPS | Progress: (20/20) | 13.63 s Done.
+[Task 5/25] Current/Best: 22.50/ 22.50 GFLOPS | Progress: (4/20) | 3.95 s
+[Task 5/25] Current/Best: 16.33/ 22.50 GFLOPS | Progress: (8/20) | 6.33 s
+[Task 5/25] Current/Best: 12.03/ 22.50 GFLOPS | Progress: (12/20) | 9.83 s
+[Task 5/25] Current/Best: 12.40/ 22.50 GFLOPS | Progress: (16/20) | 11.82 s
+[Task 5/25] Current/Best: 17.06/ 22.50 GFLOPS | Progress: (20/20) | 13.74 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 5.19/ 14.42 GFLOPS | Progress: (4/20) | 5.47 s
-[Task 6/25] Current/Best: 10.73/ 18.61 GFLOPS | Progress: (8/20) | 8.10 s
-[Task 6/25] Current/Best: 12.93/ 18.61 GFLOPS | Progress: (12/20) | 11.49 s
-[Task 6/25] Current/Best: 5.58/ 18.61 GFLOPS | Progress: (16/20) | 14.90 s
-[Task 6/25] Current/Best: 6.08/ 18.61 GFLOPS | Progress: (20/20) | 20.54 s Done.
+[Task 6/25] Current/Best: 13.10/ 15.26 GFLOPS | Progress: (4/20) | 4.62 s
+[Task 6/25] Current/Best: 3.72/ 15.26 GFLOPS | Progress: (8/20) | 8.09 s
+[Task 6/25] Current/Best: 2.90/ 15.45 GFLOPS | Progress: (12/20) | 16.20 s
+[Task 6/25] Current/Best: 2.62/ 15.45 GFLOPS | Progress: (16/20) | 19.95 s
+[Task 6/25] Current/Best: 5.76/ 15.45 GFLOPS | Progress: (20/20) | 24.56 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 16.97/ 19.07 GFLOPS | Progress: (4/20) | 4.77 s
-[Task 7/25] Current/Best: 15.25/ 19.07 GFLOPS | Progress: (8/20) | 6.97 s
-[Task 7/25] Current/Best: 8.27/ 19.07 GFLOPS | Progress: (12/20) | 9.59 s
-[Task 7/25] Current/Best: 10.79/ 19.91 GFLOPS | Progress: (16/20) | 12.55 s
-[Task 7/25] Current/Best: 15.32/ 19.91 GFLOPS | Progress: (20/20) | 15.39 s Done.
+[Task 7/25] Current/Best: 18.07/ 21.63 GFLOPS | Progress: (4/20) | 3.93 s
+[Task 7/25] Current/Best: 19.61/ 21.63 GFLOPS | Progress: (8/20) | 6.36 s
+[Task 7/25] Current/Best: 15.27/ 21.63 GFLOPS | Progress: (12/20) | 10.01 s
+[Task 7/25] Current/Best: 19.25/ 21.63 GFLOPS | Progress: (16/20) | 12.55 s
+[Task 7/25] Current/Best: 15.44/ 21.63 GFLOPS | Progress: (20/20) | 14.86 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 2.49/ 10.53 GFLOPS | Progress: (4/20) | 10.31 s
-[Task 8/25] Current/Best: 12.41/ 12.41 GFLOPS | Progress: (8/20) | 16.36 s
-[Task 8/25] Current/Best: 7.69/ 18.34 GFLOPS | Progress: (12/20) | 20.14 s
-[Task 8/25] Current/Best: 18.00/ 18.34 GFLOPS | Progress: (16/20) | 22.20 s
-[Task 8/25] Current/Best: 6.99/ 18.34 GFLOPS | Progress: (20/20) | 28.07 s Done.
-
+[Task 8/25] Current/Best: 13.99/ 13.99 GFLOPS | Progress: (4/20) | 7.20 s
+[Task 8/25] Current/Best: 11.36/ 13.99 GFLOPS | Progress: (8/20) | 19.00 s
+[Task 8/25] Current/Best: 9.32/ 13.99 GFLOPS | Progress: (12/20) | 28.01 s
+[Task 8/25] Current/Best: 12.92/ 14.32 GFLOPS | Progress: (16/20) | 31.44 s
+[Task 8/25] Current/Best: 14.42/ 14.42 GFLOPS | Progress: (20/20) | 34.09 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 17.31/ 18.98 GFLOPS | Progress: (4/20) | 4.12 s
-[Task 9/25] Current/Best: 13.12/ 20.37 GFLOPS | Progress: (8/20) | 7.67 s
-[Task 9/25] Current/Best: 9.09/ 20.37 GFLOPS | Progress: (12/20) | 13.09 s
-[Task 9/25] Current/Best: 13.75/ 20.37 GFLOPS | Progress: (16/20) | 15.04 s
-[Task 9/25] Current/Best: 15.14/ 20.37 GFLOPS | Progress: (20/20) | 22.91 s Done.
+[Task 9/25] Current/Best: 10.72/ 21.23 GFLOPS | Progress: (4/20) | 4.49 s
+[Task 9/25] Current/Best: 11.52/ 21.23 GFLOPS | Progress: (8/20) | 7.21 s
+[Task 9/25] Current/Best: 11.32/ 21.23 GFLOPS | Progress: (12/20) | 10.40 s
+[Task 9/25] Current/Best: 10.15/ 21.23 GFLOPS | Progress: (16/20) | 13.38 s
+[Task 9/25] Current/Best: 21.39/ 21.39 GFLOPS | Progress: (20/20) | 19.26 s Done.
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 13.89/ 13.89 GFLOPS | Progress: (4/20) | 4.14 s
-[Task 10/25] Current/Best: 9.49/ 16.16 GFLOPS | Progress: (8/20) | 5.82 s
-[Task 10/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (12/20) | 7.54 s
-[Task 10/25] Current/Best: 10.21/ 20.66 GFLOPS | Progress: (16/20) | 9.61 s
-[Task 10/25] Current/Best: 10.56/ 20.66 GFLOPS | Progress: (20/20) | 12.17 s Done.
+[Task 10/25] Current/Best: 9.11/ 20.57 GFLOPS | Progress: (4/20) | 3.59 s
+[Task 10/25] Current/Best: 11.82/ 20.57 GFLOPS | Progress: (8/20) | 5.92 s
+[Task 10/25] Current/Best: 9.54/ 20.57 GFLOPS | Progress: (12/20) | 7.66 s
+[Task 10/25] Current/Best: 18.41/ 20.57 GFLOPS | Progress: (16/20) | 9.94 s
+[Task 10/25] Current/Best: 15.59/ 20.57 GFLOPS | Progress: (20/20) | 11.71 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 21.30/ 21.30 GFLOPS | Progress: (4/20) | 4.28 s
-[Task 11/25] Current/Best: 9.81/ 21.30 GFLOPS | Progress: (8/20) | 6.55 s
-[Task 11/25] Current/Best: 13.39/ 21.30 GFLOPS | Progress: (12/20) | 8.99 s
-[Task 11/25] Current/Best: 7.08/ 21.30 GFLOPS | Progress: (16/20) | 11.95 s
-[Task 11/25] Current/Best: 15.47/ 21.30 GFLOPS | Progress: (20/20) | 14.49 s Done.
+[Task 11/25] Current/Best: 12.86/ 16.90 GFLOPS | Progress: (4/20) | 3.90 s
+[Task 11/25] Current/Best: 10.00/ 22.05 GFLOPS | Progress: (8/20) | 6.21 s
+[Task 11/25] Current/Best: 20.18/ 22.05 GFLOPS | Progress: (12/20) | 8.56 s
+[Task 11/25] Current/Best: 23.20/ 23.20 GFLOPS | Progress: (16/20) | 11.21 s
+[Task 11/25] Current/Best: 9.29/ 23.20 GFLOPS | Progress: (20/20) | 13.42 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 14.32/ 14.93 GFLOPS | Progress: (4/20) | 4.92 s
-[Task 12/25] Current/Best: 11.28/ 14.93 GFLOPS | Progress: (8/20) | 9.30 s
-[Task 12/25] Current/Best: 10.70/ 14.93 GFLOPS | Progress: (12/20) | 11.85 s
-[Task 12/25] Current/Best: 14.53/ 20.88 GFLOPS | Progress: (16/20) | 14.46 s
-[Task 12/25] Current/Best: 4.39/ 20.88 GFLOPS | Progress: (20/20) | 17.35 s Done.
+[Task 12/25] Current/Best: 3.48/ 12.17 GFLOPS | Progress: (4/20) | 6.21 s
+[Task 12/25] Current/Best: 8.11/ 16.26 GFLOPS | Progress: (8/20) | 8.65 s
+[Task 12/25] Current/Best: 19.55/ 19.55 GFLOPS | Progress: (12/20) | 11.03 s
+[Task 12/25] Current/Best: 12.76/ 19.55 GFLOPS | Progress: (16/20) | 15.24 s
+[Task 12/25] Current/Best: 17.53/ 19.55 GFLOPS | Progress: (20/20) | 18.83 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 11.75/ 18.52 GFLOPS | Progress: (4/20) | 4.17 s
-[Task 13/25] Current/Best: 6.14/ 18.52 GFLOPS | Progress: (8/20) | 8.05 s
-[Task 13/25] Current/Best: 17.59/ 18.52 GFLOPS | Progress: (12/20) | 12.08 s
-[Task 13/25] Current/Best: 11.79/ 20.10 GFLOPS | Progress: (16/20) | 14.56 s
-[Task 13/25] Current/Best: 3.11/ 20.10 GFLOPS | Progress: (20/20) | 18.07 s Done.
+[Task 13/25] Current/Best: 8.04/ 14.74 GFLOPS | Progress: (4/20) | 4.85 s
+[Task 13/25] Current/Best: 14.34/ 18.23 GFLOPS | Progress: (8/20) | 7.05 s
+[Task 13/25] Current/Best: 6.09/ 21.58 GFLOPS | Progress: (12/20) | 10.06 s
+[Task 13/25] Current/Best: 8.29/ 21.58 GFLOPS | Progress: (16/20) | 13.98 s
+[Task 13/25] Current/Best: 12.58/ 21.58 GFLOPS | Progress: (20/20) | 17.02 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 16.94/ 16.94 GFLOPS | Progress: (4/20) | 3.25 s
-[Task 14/25] Current/Best: 5.09/ 19.91 GFLOPS | Progress: (8/20) | 6.50 s
-[Task 14/25] Current/Best: 9.42/ 19.91 GFLOPS | Progress: (12/20) | 15.48 s
-[Task 14/25] Current/Best: 13.57/ 19.91 GFLOPS | Progress: (16/20) | 22.77 s
-[Task 14/25] Current/Best: 13.71/ 19.91 GFLOPS | Progress: (20/20) | 26.67 s
-[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.87/ 16.87 GFLOPS | Progress: (4/20) | 7.48 s
-[Task 15/25] Current/Best: 16.89/ 16.89 GFLOPS | Progress: (8/20) | 10.07 s
-[Task 15/25] Current/Best: 12.91/ 17.92 GFLOPS | Progress: (12/20) | 11.76 s Done.
-
-[Task 15/25] Current/Best: 14.06/ 17.92 GFLOPS | Progress: (16/20) | 14.88 s
-[Task 15/25] Current/Best: 23.16/ 23.16 GFLOPS | Progress: (20/20) | 16.38 s
+[Task 14/25] Current/Best: 2.45/ 10.90 GFLOPS | Progress: (4/20) | 5.24 s
+[Task 14/25] Current/Best: 9.30/ 17.68 GFLOPS | Progress: (8/20) | 9.91 s
+[Task 14/25] Current/Best: 12.88/ 17.68 GFLOPS | Progress: (12/20) | 13.41 s
+[Task 14/25] Current/Best: 21.08/ 21.08 GFLOPS | Progress: (16/20) | 18.08 s
+[Task 14/25] Current/Best: 16.73/ 21.08 GFLOPS | Progress: (20/20) | 19.71 s
+[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
+[Task 15/25] Current/Best: 16.41/ 16.41 GFLOPS | Progress: (4/20) | 4.54 s
+[Task 15/25] Current/Best: 9.49/ 16.41 GFLOPS | Progress: (8/20) | 8.61 s
+[Task 15/25] Current/Best: 6.19/ 20.03 GFLOPS | Progress: (12/20) | 10.43 s
+[Task 15/25] Current/Best: 10.53/ 22.37 GFLOPS | Progress: (16/20) | 15.23 s
+[Task 15/25] Current/Best: 9.28/ 22.37 GFLOPS | Progress: (20/20) | 19.52 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 4.82/ 18.35 GFLOPS | Progress: (4/20) | 4.21 s
-[Task 16/25] Current/Best: 10.27/ 18.35 GFLOPS | Progress: (8/20) | 6.49 s
-[Task 16/25] Current/Best: 12.71/ 18.35 GFLOPS | Progress: (12/20) | 10.85 s
-[Task 16/25] Current/Best: 6.42/ 18.35 GFLOPS | Progress: (16/20) | 13.28 s
-[Task 16/25] Current/Best: 17.32/ 18.35 GFLOPS | Progress: (20/20) | 14.94 s Done.
+[Task 16/25] Current/Best: 15.78/ 21.30 GFLOPS | Progress: (4/20) | 3.30 s
+[Task 16/25] Current/Best: 12.07/ 21.30 GFLOPS | Progress: (8/20) | 6.97 s
+[Task 16/25] Current/Best: 7.58/ 21.30 GFLOPS | Progress: (12/20) | 10.36 s
+[Task 16/25] Current/Best: 20.52/ 21.30 GFLOPS | Progress: (16/20) | 13.73 s
+[Task 16/25] Current/Best: 18.51/ 21.30 GFLOPS | Progress: (20/20) | 15.31 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 3.08/ 12.21 GFLOPS | Progress: (4/20) | 4.94 s
-[Task 17/25] Current/Best: 13.13/ 17.71 GFLOPS | Progress: (8/20) | 8.13 s
-[Task 17/25] Current/Best: 18.65/ 18.65 GFLOPS | Progress: (12/20) | 10.62 s
-[Task 17/25] Current/Best: 14.54/ 18.65 GFLOPS | Progress: (16/20) | 13.38 s
-[Task 17/25] Current/Best: 16.48/ 18.65 GFLOPS | Progress: (20/20) | 16.81 s Done.
+[Task 17/25] Current/Best: 13.34/ 22.57 GFLOPS | Progress: (4/20) | 3.90 s
+[Task 17/25] Current/Best: 11.87/ 22.57 GFLOPS | Progress: (8/20) | 7.23 s
+[Task 17/25] Current/Best: 6.17/ 22.57 GFLOPS | Progress: (12/20) | 11.00 s
+[Task 17/25] Current/Best: 17.40/ 22.57 GFLOPS | Progress: (16/20) | 13.32 s
+[Task 17/25] Current/Best: 7.70/ 22.57 GFLOPS | Progress: (20/20) | 16.38 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.43/ 16.94 GFLOPS | Progress: (4/20) | 5.36 s
-[Task 18/25] Current/Best: 12.03/ 16.94 GFLOPS | Progress: (8/20) | 9.01 s
-[Task 18/25] Current/Best: 6.10/ 16.94 GFLOPS | Progress: (12/20) | 11.48 s
-[Task 18/25] Current/Best: 10.12/ 16.97 GFLOPS | Progress: (16/20) | 14.94 s
-[Task 18/25] Current/Best: 12.21/ 18.32 GFLOPS | Progress: (20/20) | 17.91 s Done.
+[Task 18/25] Current/Best: 15.29/ 15.95 GFLOPS | Progress: (4/20) | 4.23 s
+[Task 18/25] Current/Best: 20.44/ 20.44 GFLOPS | Progress: (8/20) | 6.45 s
+[Task 18/25] Current/Best: 10.66/ 20.44 GFLOPS | Progress: (12/20) | 10.36 s
+[Task 18/25] Current/Best: 9.59/ 20.44 GFLOPS | Progress: (16/20) | 13.94 s
+[Task 18/25] Current/Best: 16.98/ 20.44 GFLOPS | Progress: (20/20) | 15.84 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 5.35/ 22.04 GFLOPS | Progress: (4/20) | 5.33 s
-[Task 19/25] Current/Best: 9.79/ 22.04 GFLOPS | Progress: (8/20) | 8.55 s
-[Task 19/25] Current/Best: 11.96/ 22.04 GFLOPS | Progress: (12/20) | 12.80 s
-[Task 19/25] Current/Best: 8.81/ 22.04 GFLOPS | Progress: (16/20) | 15.80 s
-[Task 19/25] Current/Best: 7.46/ 22.04 GFLOPS | Progress: (20/20) | 19.37 s Done.
+[Task 19/25] Current/Best: 17.15/ 17.94 GFLOPS | Progress: (4/20) | 5.33 s
+[Task 19/25] Current/Best: 16.78/ 17.94 GFLOPS | Progress: (8/20) | 8.88 s
+[Task 19/25] Current/Best: 6.29/ 18.45 GFLOPS | Progress: (12/20) | 12.60 s
+[Task 19/25] Current/Best: 13.10/ 21.39 GFLOPS | Progress: (16/20) | 16.24 s
+[Task 19/25] Current/Best: 11.29/ 22.46 GFLOPS | Progress: (20/20) | 19.52 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.59/ 18.29 GFLOPS | Progress: (4/20) | 4.86 s
-[Task 20/25] Current/Best: 7.11/ 18.29 GFLOPS | Progress: (8/20) | 9.40 s
-[Task 20/25] Current/Best: 6.81/ 18.29 GFLOPS | Progress: (12/20) | 11.99 s
-[Task 20/25] Current/Best: 16.89/ 18.29 GFLOPS | Progress: (16/20) | 14.70 s
-[Task 20/25] Current/Best: 14.01/ 18.29 GFLOPS | Progress: (20/20) | 17.72 s
+[Task 20/25] Current/Best: 15.87/ 18.90 GFLOPS | Progress: (4/20) | 4.24 s
+[Task 20/25] Current/Best: 16.92/ 18.90 GFLOPS | Progress: (8/20) | 6.38 s
+[Task 20/25] Current/Best: 13.30/ 18.90 GFLOPS | Progress: (12/20) | 9.43 s
+[Task 20/25] Current/Best: 16.29/ 18.90 GFLOPS | Progress: (16/20) | 12.89 s
+[Task 20/25] Current/Best: 18.46/ 18.90 GFLOPS | Progress: (20/20) | 15.30 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 18.84/ 18.84 GFLOPS | Progress: (4/20) | 4.26 s
-[Task 21/25] Current/Best: 8.96/ 18.84 GFLOPS | Progress: (8/20) | 5.78 s
-[Task 21/25] Current/Best: 2.72/ 18.84 GFLOPS | Progress: (12/20) | 13.56 s Done.
- Done.
+[Task 21/25] Current/Best: 7.33/ 9.77 GFLOPS | Progress: (4/20) | 4.11 s
+[Task 21/25] Current/Best: 12.73/ 12.73 GFLOPS | Progress: (8/20) | 6.64 s
+[Task 21/25] Current/Best: 17.92/ 21.26 GFLOPS | Progress: (12/20) | 8.87 s
+[Task 21/25] Current/Best: 9.99/ 21.26 GFLOPS | Progress: (16/20) | 11.01 s Done.
+
+[Task 21/25] Current/Best: 14.43/ 21.26 GFLOPS | Progress: (20/20) | 13.27 s Done.
-[Task 21/25] Current/Best: 16.28/ 20.81 GFLOPS | Progress: (16/20) | 16.00 s
-[Task 21/25] Current/Best: 14.13/ 20.81 GFLOPS | Progress: (20/20) | 17.65 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 8.00/ 20.80 GFLOPS | Progress: (4/20) | 4.85 s
-[Task 22/25] Current/Best: 9.72/ 22.91 GFLOPS | Progress: (8/20) | 6.52 s
-[Task 22/25] Current/Best: 6.26/ 22.91 GFLOPS | Progress: (12/20) | 10.96 s
-[Task 22/25] Current/Best: 9.44/ 22.91 GFLOPS | Progress: (16/20) | 13.05 s
-[Task 22/25] Current/Best: 10.13/ 22.91 GFLOPS | Progress: (20/20) | 15.45 s Done.
+[Task 22/25] Current/Best: 5.21/ 13.66 GFLOPS | Progress: (4/20) | 4.08 s
+[Task 22/25] Current/Best: 17.97/ 17.97 GFLOPS | Progress: (8/20) | 6.37 s
+[Task 22/25] Current/Best: 18.50/ 18.50 GFLOPS | Progress: (12/20) | 8.32 s
+[Task 22/25] Current/Best: 9.68/ 18.50 GFLOPS | Progress: (16/20) | 10.59 s
+[Task 22/25] Current/Best: 4.45/ 18.50 GFLOPS | Progress: (20/20) | 13.06 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 9.97/ 22.61 GFLOPS | Progress: (4/20) | 4.17 s
-[Task 23/25] Current/Best: 12.23/ 22.61 GFLOPS | Progress: (8/20) | 6.92 s
-[Task 23/25] Current/Best: 7.83/ 22.61 GFLOPS | Progress: (12/20) | 10.13 s
-[Task 23/25] Current/Best: 21.39/ 22.92 GFLOPS | Progress: (16/20) | 12.96 s
-[Task 23/25] Current/Best: 10.62/ 22.92 GFLOPS | Progress: (20/20) | 15.91 s Done.
+[Task 23/25] Current/Best: 2.67/ 18.67 GFLOPS | Progress: (4/20) | 4.69 s
+[Task 23/25] Current/Best: 12.32/ 18.67 GFLOPS | Progress: (8/20) | 7.92 s
+[Task 23/25] Current/Best: 19.65/ 19.65 GFLOPS | Progress: (12/20) | 13.04 s
+[Task 23/25] Current/Best: 6.14/ 22.04 GFLOPS | Progress: (16/20) | 15.80 s
+[Task 23/25] Current/Best: 4.87/ 22.04 GFLOPS | Progress: (20/20) | 19.23 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 9.14/ 9.48 GFLOPS | Progress: (4/20) | 9.97 s
-[Task 24/25] Current/Best: 3.35/ 9.48 GFLOPS | Progress: (8/20) | 20.65 s
-[Task 24/25] Current/Best: 8.86/ 9.48 GFLOPS | Progress: (12/20) | 32.50 s
-[Task 24/25] Current/Best: 2.81/ 9.48 GFLOPS | Progress: (16/20) | 43.45 s
-[Task 24/25] Current/Best: 3.59/ 9.48 GFLOPS | Progress: (20/20) | 54.98 s
+[Task 24/25] Current/Best: 3.50/ 3.50 GFLOPS | Progress: (4/20) | 12.15 s
+[Task 24/25] Current/Best: 2.80/ 9.97 GFLOPS | Progress: (8/20) | 23.90 s
+[Task 24/25] Current/Best: 2.36/ 9.97 GFLOPS | Progress: (12/20) | 26.81 s
+[Task 24/25] Current/Best: 3.82/ 9.97 GFLOPS | Progress: (16/20) | 31.71 s
+[Task 24/25] Current/Best: 5.50/ 9.97 GFLOPS | Progress: (20/20) | 42.66 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-[Task 25/25] Current/Best: 5.74/ 5.74 GFLOPS | Progress: (4/20) | 4.29 s
-[Task 25/25] Current/Best: 3.65/ 5.74 GFLOPS | Progress: (8/20) | 9.90 s
-[Task 25/25] Current/Best: 3.01/ 9.40 GFLOPS | Progress: (12/20) | 14.90 s
-[Task 25/25] Current/Best: 1.55/ 9.40 GFLOPS | Progress: (16/20) | 25.86 s
-[Task 25/25] Current/Best: 3.45/ 9.40 GFLOPS | Progress: (20/20) | 37.35 s
+[Task 25/25] Current/Best: 7.39/ 7.69 GFLOPS | Progress: (4/20) | 3.88 s
+[Task 25/25] Current/Best: 5.23/ 7.69 GFLOPS | Progress: (8/20) | 14.82 s
+[Task 25/25] Current/Best: 4.06/ 7.69 GFLOPS | Progress: (12/20) | 25.75 s
+[Task 25/25] Current/Best: 3.50/ 7.69 GFLOPS | Progress: (16/20) | 27.87 s
+[Task 25/25] Current/Best: 8.54/ 8.54 GFLOPS | Progress: (20/20) | 38.79 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -943,8 +942,8 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
-class='n02123159 tiger cat' with probability=0.356378
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621103
+class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -981,8 +980,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 427.9868124599989, 'median': 426.6517240999974, 'std': 3.5526446388610853}
-unoptimized: {'mean': 517.6232956799993, 'median': 517.659318699998, 'std': 1.5351246130381426}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 411.6475026200351, 'median': 412.2672734001753, 'std': 3.0716165239000963}
+unoptimized: {'mean': 514.1060797499813, 'median': 513.3606129998952, 'std': 2.953015519281599}
</pre></div>
</div>
</div>
@@ -996,7 +995,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 12 minutes 9.178 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 11 minutes 38.791 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index 917c81a8ba..cb660941cc 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -538,7 +538,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.278e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.288e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 4937d3d0f2..0c667662ab 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -508,7 +508,7 @@ class Module:
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x10952740)), stage(b, placeholder(b, 0xcd55990)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attrs [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x198303f0)), stage(b, placeholder(b, 0x20a42140)), stage(T_add, compute(T_add, body=[a[ax0, ax1, ax2] + b[ax1, ax2]], axis=[T.iter_var(ax0, T.Range(0, 100), "DataPar", ""), T.iter_var(ax1, T.Range(0, 10), "DataPar", ""), T.iter_var(ax2, T.Range(0, 10), "DataPar", "")], reduce_axis=[], tag=broadcast, attr [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index c46ad8f4d6..0939d6641f 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -340,7 +340,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>15:55.014</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>15:06.764</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -349,42 +349,42 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>12:09.178</p></td>
+<td><p>11:38.791</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>01:38.354</p></td>
+<td><p>01:29.212</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:01.200</p></td>
+<td><p>00:58.977</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:36.033</p></td>
+<td><p>00:34.798</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:27.835</p></td>
+<td><p>00:23.385</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.406</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
+<td><p>00:00.819</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
-<td><p>00:00.838</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
+<td><p>00:00.619</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.170</p></td>
+<td><p>00:00.162</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="uma.html#sphx-glr-tutorial-uma-py"><span class="std std-ref">Making your Hardware Accelerator TVM-ready with UMA</span></a> (<code class="docutils literal notranslate"><span class="pre">uma.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 4702272683..4087767907 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -549,8 +549,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
-naive: 0.000008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000007
+naive: 0.000007
</pre></div>
</div>
</div>
@@ -681,10 +681,10 @@ class Module:
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 7.75676000102976e-06 1.0
- naive 7.841299999999999e-06 1.010898880326195
-parallel 6.945800000000001e-06 0.8954511934206938
- vector 2.4883400000000003e-05 3.207963118195815
+ numpy 7.2933599949465134e-06 1.0
+ naive 6.6998e-06 0.9186163859513606
+parallel 6.995700000000001e-06 0.9591875356279194
+ vector 2.47294e-05 3.3906731625937456
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -1000,7 +1000,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018577
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017826
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1041,7 +1041,7 @@ optimizations.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.402429
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>none: 3.263024
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1105,7 +1105,7 @@ schedule.</p>
<span class="n">evaluate_operation</span><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">s</span></a><span class="p">,</span> <span class="p">[</span><a href="../reference/api/python/te.html#tvm.te.Tensor" title="tvm.te.Tensor" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.313091
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>blocking: 0.298400
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1154,7 +1154,7 @@ already cache friendly from our previous optimizations.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.343664
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vectorization: 0.335828
@I.ir_module
class Module:
@T.prim_func
@@ -1203,7 +1203,7 @@ more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.117127
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>loop permutation: 0.116744
@I.ir_module
class Module:
@T.prim_func
@@ -1273,7 +1273,7 @@ optimized schedule.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.108402
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>array packing: 0.109167
@I.ir_module
class Module:
@T.prim_func
@@ -1339,7 +1339,7 @@ to `C</cite> when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.111008
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>block caching: 0.110256
@I.ir_module
class Module:
@T.prim_func
@@ -1396,7 +1396,7 @@ of thread-level parallelization.</p>
<span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/driver.html#tvm.lower" title="tvm.lower" class="sphx-glr-backref-module-tvm sphx-glr-backref-type-py-function"><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span></a><span class="p">(</span><a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.147413
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>parallelization: 0.146220
@I.ir_module
class Module:
@T.prim_func
@@ -1449,13 +1449,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.4024285011 1.0
- blocking 0.31309147660000003 0.09202000174251362
- vectorization 0.34366443789999995 0.10100563106289927
-loop permutation 0.11712691290000002 0.0344245038101853
- array packing 0.10840182999999999 0.031860134596495955
- block caching 0.1110082867 0.03262619234000397
- parallelization 0.1474132279 0.04332588557036291
+ none 3.2630241653 1.0
+ blocking 0.2984000276 0.09144891747149085
+ vectorization 0.3358284045 0.10291937401852622
+loop permutation 0.11674430870000001 0.03577794793599594
+ array packing 0.10916693 0.03345575284452828
+ block caching 0.1102562794 0.033789599406740256
+ parallelization 0.14622028609999999 0.04481127895249792
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1487,7 +1487,6 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.200 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tensor_expr_get_started.py</span></code></a></p>