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 2022/06/29 23:08:22 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@b552bcf1d0584a8ba64915be2efa7daf8907b8e3)
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 c7fe387d9 deploying docs (apache/tvm@b552bcf1d0584a8ba64915be2efa7daf8907b8e3)
c7fe387d9 is described below
commit c7fe387d9f122299490108d6c6be22952d8e7b00
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Jun 29 23:08:17 2022 +0000
deploying docs (apache/tvm@b552bcf1d0584a8ba64915be2efa7daf8907b8e3)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 5 -
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../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 | 16 +-
.../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 | 1267 ++++++++++++++++++--
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 24 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 8 +-
.../work_with_relay/sg_execution_times.rst.txt | 6 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 16 +-
.../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 | 2 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 18 +-
.../tutorial/tensor_expr_get_started.rst.txt | 45 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 79 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 1 -
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 20 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 22 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 18 +-
.../tune_conv2d_layer_cuda.html | 1267 ++++++++++++++++++--
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 24 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/sg_execution_times.html | 6 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 16 +-
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 | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 2 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 18 +-
docs/tutorial/tensor_expr_get_started.html | 41 +-
121 files changed, 3224 insertions(+), 1009 deletions(-)
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 c28dbe7df..c4d323b82 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -114,7 +114,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipad583a90-6d99-428d-a92a-b5517dfddab7 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf338fb74-416f-4c38-a80a-c5adf8387794 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 f2d8cba25..aa5e11c68 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -112,7 +112,7 @@ 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]
0%| | 16.0k/41.5M [00:00<08:11, 88.5kB/s]
0%| | 48.0k/41.5M [00:00<05:10, 140kB/s]
0%| | 96.0k/41.5M [00:00<03:40, 197kB/s]
0%| | 208k/41.5M [00:00<01:59, 362kB/s]
1%|1 | 432k/41.5M [00:00<01:03, 676kB/s]
2%|2 | 872k/41.5M [00:01<00:33, 1.27MB/s]
4%|4 | 1.72M/41.5M [00:01<00:17, 2.45MB/s]
8%|7 | 3.20M/41.5M [00:01<00:09, 4.32MB/s]
11%|#1 | 4.67M/41.5M [00:01<00:06, 5.57MB/s]
15%|#4 | 6.15M/41.5M [00:01<00:05, 6.42MB/s]
18%|#8 | 7.62M/41.5M [00:02<00:05, 7.00MB/s]
22%|##1 | 9.10M/41.5M [00:02<00:04, 7.40MB/s]
25%|##5 | 10.6M/41.5M [00:02<00:04, 7.68MB/s]
29%|##9 | 12.1M/41.5M [00:02<00:03, 7.87MB/s]
33%|###2 | 13.5M/41.5M [00:02<00:03, 8.01MB/s]
36%|###6 | 15.0M/41.5M [00:02<00:03, 8.11MB/s]
40%|###9 | 16.5M/41.5M [00:03<0
0:03, 8.17MB/s]
43%|####3 | 18.0M/41.5M [00:03<00:03, 8.19MB/s]
47%|####6 | 19.4M/41.5M [00:03<00:02, 9.44MB/s]
49%|####9 | 20.4M/41.5M [00:03<00:02, 9.54MB/s]
51%|#####1 | 21.4M/41.5M [00:03<00:02, 8.37MB/s]
54%|#####3 | 22.4M/41.5M [00:03<00:02, 7.53MB/s]
58%|#####7 | 23.9M/41.5M [00:04<00:02, 7.79MB/s]
61%|######1 | 25.3M/41.5M [00:04<00:02, 7.96MB/s]
65%|######4 | 26.8M/41.5M [00:04<00:01, 8.43MB/s]
68%|######8 | 28.3M/41.5M [00:04<00:01, 9.70MB/s]
71%|####### | 29.3M/41.5M [00:04<00:01, 8.92MB/s]
73%|#######2 | 30.2M/41.5M [00:04<00:01, 8.18MB/s]
75%|#######4 | 31.0M/41.5M [00:05<00:01, 6.86MB/s]
77%|#######6 | 31.8M/41.5M [00:05<00:01, 6.15MB/s]
78%|#######8 | 32.6M/41.5M [00:05<00:01, 5.54MB/s]
82%|########1 | 34.0M/41.5M [00:05<00:01, 6.38MB/s]
85%|########4 | 35.2M/41.5M [00:05<00:01, 6.51MB/s]
88%|########8 | 36.7M/41.5M [00:05<00:00, 7.05MB/s]
90%|###
###### | 37.4M/41.5M [00:06<00:00, 6.03MB/s]
93%|#########3| 38.8M/41.5M [00:06<00:00, 6.60MB/s]
96%|#########5| 39.6M/41.5M [00:06<00:00, 6.10MB/s]
99%|#########9| 41.1M/41.5M [00:06<00:00, 6.76MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 6.48MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:05, 89.5kB/s]
0%| | 40.0k/41.5M [00:00<06:16, 116kB/s]
0%| | 96.0k/41.5M [00:00<03:31, 205kB/s]
0%| | 160k/41.5M [00:00<02:43, 265kB/s]
1%| | 272k/41.5M [00:00<01:49, 394kB/s]
1%|1 | 560k/41.5M [00:01<00:53, 805kB/s]
2%|2 | 864k/41.5M [00:01<00:38, 1.10MB/s]
4%|3 | 1.63M/41.5M [00:01<00:19, 2.18MB/s]
7%|7 | 3.11M/41.5M [00:01<00:09, 4.13MB/s]
11%|# | 4.55M/41.5M [00:01<00:07, 5.38MB/s]
15%|#4 | 6.02M/41.5M [00:02<00:05, 6.31MB/s]
18%|#8 | 7.50M/41.5M [00:02<00:05, 6.95MB/s]
22%|##1 | 8.98M/41.5M [00:02<00:04, 7.39MB/s]
25%|##5 | 10.5M/41.5M [00:02<00:04, 7.66MB/s]
29%|##8 | 11.9M/41.5M [00:02<00:03, 8.93MB/s]
32%|###2 | 13.3M/41.5M [00:02<00:02, 10.0MB/s]
35%|###4 | 14.4M/41.5M [00:02<00:
03, 9.08MB/s]
37%|###6 | 15.3M/41.5M [00:03<00:03, 7.81MB/s]
39%|###9 | 16.4M/41.5M [00:03<00:03, 7.25MB/s]
43%|####2 | 17.8M/41.5M [00:03<00:03, 7.64MB/s]
47%|####6 | 19.3M/41.5M [00:03<00:02, 7.89MB/s]
50%|##### | 20.8M/41.5M [00:03<00:02, 8.06MB/s]
54%|#####3 | 22.3M/41.5M [00:04<00:02, 8.17MB/s]
57%|#####7 | 23.7M/41.5M [00:04<00:02, 9.24MB/s]
61%|###### | 25.1M/41.5M [00:04<00:01, 10.3MB/s]
63%|######3 | 26.2M/41.5M [00:04<00:01, 9.31MB/s]
65%|######5 | 27.2M/41.5M [00:04<00:01, 8.01MB/s]
68%|######7 | 28.2M/41.5M [00:04<00:01, 8.33MB/s]
71%|#######1 | 29.6M/41.5M [00:04<00:01, 9.73MB/s]
74%|#######3 | 30.6M/41.5M [00:04<00:01, 8.71MB/s]
76%|#######5 | 31.5M/41.5M [00:05<00:01, 7.44MB/s]
78%|#######8 | 32.5M/41.5M [00:05<00:01, 8.12MB/s]
82%|########1 | 34.0M/41.5M [00:05<00:00, 9.68MB/s]
84%|########4 | 35.0M/41.5M [00:05<00:00, 8.66MB/s]
87%|#####
###6 | 35.9M/41.5M [00:05<00:00, 7.43MB/s]
89%|########9 | 37.0M/41.5M [00:05<00:00, 7.06MB/s]
93%|#########2| 38.4M/41.5M [00:06<00:00, 7.51MB/s]
96%|#########6| 39.9M/41.5M [00:06<00:00, 7.79MB/s]
100%|#########9| 41.4M/41.5M [00:06<00:00, 7.97MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 6.75MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index bf93e7d20..c8a375eb5 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -235,7 +235,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 33.147 seconds)
+ **Total running time of the script:** ( 1 minutes 10.314 seconds)
.. _sphx_glr_download_how_to_compile_models_from_paddle.py:
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 d593a738e..221ebe0df 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -93,7 +93,7 @@ Load a pretrained PyTorch model
.. code-block:: none
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]
37%|###7 | 16.7M/44.7M [00:00<00:00, 175MB/s]
90%|########9 | 40.1M/44.7M [00:00<00:00, 217MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 214MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
39%|###9 | 17.5M/44.7M [00:00<00:00, 184MB/s]
93%|#########2| 41.5M/44.7M [00:00<00:00, 224MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 220MB/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 b75e0935f..7c54c71bb 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -420,11 +420,6 @@ Run the corresponding model on tensorflow
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.396 seconds)
-
-
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
.. only:: html
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 57904e4a8..52d3d0af4 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
=================
-**05:50.529** total execution time for **how_to_compile_models** files:
+**05:40.801** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:33.147 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:10.314 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.396 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 00:59.945 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:57.265 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:56.420 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.869 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:42.625 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.353 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.791 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:23.098 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:22.901 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.846 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.577 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:18.997 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:18.875 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.286 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:13.843 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.271 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.511 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
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 dcef1aa65..56a5593b6 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
@@ -440,7 +440,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3903 16.4060 16.5603 16.2809 0.0777
+ 16.3799 16.6577 16.9003 15.6369 0.4636
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 fa06ae5f1..de58a9ea4 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
@@ -122,7 +122,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
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]
3%|3 | 5.35M/170M [00:00<00:03, 56.1MB/s]
6%|6 | 10.7M/170M [00:00<00:03, 55.2MB/s]
20%|## | 34.3M/170M [00:00<00:00, 142MB/s]
33%|###2 | 55.8M/170M [00:00<00:00, 175MB/s]
46%|####5 | 77.3M/170M [00:00<00:00, 193MB/s]
59%|#####8 | 100M/170M [00:00<00:00, 208MB/s]
71%|#######1 | 121M/170M [00:00<00:00, 212MB/s]
84%|########4 | 143M/170M [00:00<00:00, 217MB/s]
97%|#########6| 165M/170M [00:00<00:00, 221MB/s]
100%|##########| 170M/170M [00:00<00:00, 193MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 4.03M/170M [00:00<00:04, 42.2MB/s]
5%|5 | 8.75M/170M [00:00<00:03, 46.5MB/s]
20%|## | 34.1M/170M [00:00<00:00, 147MB/s]
36%|###6 | 61.7M/170M [00:00<00:00, 203MB/s]
53%|#####2 | 90.0M/170M [00:00<00:00, 237MB/s]
70%|######9 | 118M/170M [00:00<00:00, 257MB/s]
86%|########6 | 146M/170M [00:00<00:00, 269MB/s]
100%|##########| 170M/170M [00:00<00:00, 225MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: 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)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: 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').
@@ -291,7 +291,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 4.111 seconds)
+ **Total running time of the script:** ( 2 minutes 51.314 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 39a006bc6..7bf4d0113 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -219,7 +219,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
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]
100%|##########| 13.6M/13.6M [00:00<00:00, 181MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 186MB/s]
@@ -399,7 +399,7 @@ 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)
- 90.4675 90.3879 95.3678 90.1745 0.5082
+ 90.3545 90.2167 95.0284 90.0519 0.6304
@@ -448,7 +448,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.767 seconds)
+ **Total running time of the script:** ( 1 minutes 5.868 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 00391b0bc..2cc5af202 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
@@ -426,7 +426,7 @@ 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)
- 119.2313 119.0809 126.9910 118.1904 0.9721
+ 119.0591 119.0262 124.0607 118.4468 0.5675
@@ -463,7 +463,7 @@ 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:** ( 1 minutes 59.088 seconds)
+ **Total running time of the script:** ( 1 minutes 49.711 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 9b7cb6322..4566ef1c5 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -254,7 +254,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 2.257 seconds)
+ **Total running time of the script:** ( 1 minutes 11.787 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 ef96f7e76..6283b2963 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
@@ -157,7 +157,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6354/132723 [00:00<00:01, 63533.85KB/s]
11%|# | 14220/132723 [00:00<00:01, 72426.09KB/s]
16%|#6 | 21463/132723 [00:00<00:01, 69848.05KB/s]
22%|##2 | 29416/132723 [00:00<00:01, 73585.20KB/s]
28%|##7 | 36790/132723 [00:00<00:01, 68170.99KB/s]
34%|###3 | 44723/132723 [00:00<00:01, 71738.02KB/s]
40%|###9 | 52641/132723 [00:00<00:01, 74070.58KB/s]
46%|####5 | 60507/132723 [00:00<00:00, 75483.29KB/s]
51%|#####1 | 68097/132723 [00:00<00:00, 73977.71KB/s]
57%|#####7 | 76033/132723 [00:01<00:00, 75589.90KB/s]
63%|######3 | 84021/132723 [00:01<00:00, 76873.51KB/s]
69%|######9 | 91978/132723 [00:01<00:00, 77680.77KB/s]
75%|#######5 | 99941/132723 [00:01<00:00, 78263.85KB/s]
81%|########1 | 107994/132723 [00:01<00:00, 78939.85KB/s]
87%|########7 | 115953/132723 [00:01<00:00, 79132.07KB/s]
93%|#########
3| 123873/132723 [00:01<00:00, 79034.73KB/s]
99%|#########9| 131857/132723 [00:01<00:00, 79272.95KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75813.81KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6580/132723 [00:00<00:01, 65794.26KB/s]
12%|#1 | 15390/132723 [00:00<00:01, 78911.09KB/s]
18%|#8 | 24210/132723 [00:00<00:01, 83148.01KB/s]
25%|##4 | 32892/132723 [00:00<00:01, 84594.04KB/s]
31%|###1 | 41681/132723 [00:00<00:01, 85777.15KB/s]
38%|###8 | 50491/132723 [00:00<00:00, 86563.24KB/s]
45%|####4 | 59324/132723 [00:00<00:00, 87138.71KB/s]
51%|#####1 | 68190/132723 [00:00<00:00, 87620.94KB/s]
58%|#####8 | 77068/132723 [00:00<00:00, 87979.87KB/s]
65%|######4 | 85941/132723 [00:01<00:00, 88203.54KB/s]
71%|#######1 | 94762/132723 [00:01<00:00, 88085.04KB/s]
78%|#######8 | 103598/132723 [00:01<00:00, 88167.03KB/s]
85%|########4 | 112425/132723 [00:01<00:00, 88195.43KB/s]
91%|#########1| 121270/132723 [00:01<00:00, 88270.27KB/s]
98%|#########8| 130098/132723 [00:01<00:00, 88073.42KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 86589.14KB/s]
@@ -240,7 +240,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 24.225 seconds)
+ **Total running time of the script:** ( 2 minutes 18.923 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 6dd25fd0a..8c89c52a0 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
@@ -5,22 +5,22 @@
Computation times
=================
-**12:30.837** total execution time for **how_to_deploy_models** files:
+**10:08.823** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:04.111 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:51.314 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 03:02.257 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:18.923 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:24.225 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:49.711 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:59.088 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:11.787 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.767 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:05.868 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.962 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.643 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.421 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.571 | 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 33b7186d1..597ab35a4 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.zipadf2beb8-5c45-44a9-b453-b3f610067637 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip82f61d30-ca3b-4b66-93ec-9f9a9e681d9d 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 e2aaa0c62..504453df4 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
=================
-**00:41.230** total execution time for **how_to_extend_tvm** files:
+**00:39.554** 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``) | 00:37.965 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:36.434 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.306 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.200 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.953 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.914 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.006 | 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 cdb4aa4f9..e6935310e 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
@@ -215,10 +215,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6835us [6835us] (45.24%; 45.24%)
- FoldScaleAxis: 8272us [7us] (54.76%; 54.76%)
- FoldConstant: 8265us [1591us] (54.71%; 99.91%)
- InferType: 6674us [6674us] (44.18%; 80.75%)
+ InferType: 6757us [6757us] (45.59%; 45.59%)
+ FoldScaleAxis: 8064us [5us] (54.41%; 54.41%)
+ FoldConstant: 8059us [1611us] (54.37%; 99.93%)
+ InferType: 6447us [6447us] (43.50%; 80.00%)
@@ -257,10 +257,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6471us [6471us] (44.77%; 44.77%)
- FoldScaleAxis: 7983us [6us] (55.23%; 55.23%)
- FoldConstant: 7977us [1647us] (55.19%; 99.93%)
- InferType: 6330us [6330us] (43.79%; 79.35%)
+ InferType: 6419us [6419us] (44.87%; 44.87%)
+ FoldScaleAxis: 7888us [5us] (55.13%; 55.13%)
+ FoldConstant: 7883us [1605us] (55.10%; 99.94%)
+ InferType: 6278us [6278us] (43.88%; 79.64%)
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 abb185bb7..649df4031 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
@@ -327,7 +327,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 37.193923 ms
+ Convolution: 54.147502 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 a8eab0121..96eaf2867 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
@@ -658,7 +658,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 13.388187 ms
+ conv2d with tensor core: 7.160906 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 3af249f07..f3c59411f 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -130,8 +130,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019161
- Baseline: 3.514780
+ Numpy running time: 0.018037
+ Baseline: 3.192306
@@ -226,7 +226,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.316769
+ Opt1: 0.302333
@@ -329,7 +329,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.346321
+ Opt2: 0.332278
@@ -425,7 +425,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.133215
+ Opt3: 0.117405
@@ -550,7 +550,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111473
+ Opt4: 0.111784
@@ -672,7 +672,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111385
+ Opt5: 0.111186
@@ -797,7 +797,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.146088
+ Opt6: 0.145332
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 da9a1113a..bec4856b5 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
=================
-**00:35.506** total execution time for **how_to_optimize_operators** files:
+**00:33.713** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.464 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.377 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.246 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.029 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.003 | 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 d01e4cddc..6a07b0d98 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
=================
-**05:13.679** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:14.796** 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``) | 02:33.234 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:38.971 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.556 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:19.510 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:44.147 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:42.913 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:17.066 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:16.671 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.844 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.453 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.832 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.279 | 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 c64d29aff..5a8bc4524 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
@@ -239,39 +239,612 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
- allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [336]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- for (rx.outer.outer: int32, 0, 3) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + floordiv(threadIdx.x_1, 112)) < 3), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [336], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_1)] = @tir.if_then_else(((((1 <= (floormod(blockIdx.x, 7) + floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + floordiv(threadIdx.x_1, 7)), 3))) && ((floormod(blockIdx.x, 7) + floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + floordiv(threadIdx.x_1, 7)), 3)) < 8)) && (1 <= (rx.outer.outer + floormod(thread [...]
- }
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 37), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((threadIdx.x_1 < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else((((threadIdx.x_1 < 23) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
}
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1: int32, 0, 5) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 32)) < 32), dtype=bool) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 3) {
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*672) + (threadIdx.x_2*3)) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = kernel[(((((((floordiv(blockIdx.x, 7)*294912) + (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*64512)) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s*3)) + rx.outer.outer)]
- }
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 840), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 952), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1064), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
}
- for (rc.inner: int32, 0, 16) {
- for (ry.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*21) + (ry.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.inner*3)) + ry.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*21) + (ry.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.inner*3)) + ry.inner) + 1536)]))
- }
+ for (rc.outer.inner: int32, 0, 2) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
}
}
}
- compute[((((floordiv(blockIdx.x, 7)*3136) + (floordiv(threadIdx.x, 7)*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*64) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((((floordiv(blockIdx.x, 7)*3136) + (floordiv(threadIdx.x, 7)*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7)) + 1568)] = max((conv2d_nchw_1[1] + bias[(((floordiv(blockIdx.x, 7)*64) + floordiv(threadIdx.x, 7)) + 32)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
+ }
}
}
@@ -325,7 +898,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.409 ms
+ Execution time of this operator: 0.215 ms
@@ -374,35 +947,35 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
- 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_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=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
- conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
+ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ 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=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ 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=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -420,16 +993,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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=3)
+ 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=224)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
+ 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:
@@ -447,38 +1020,576 @@ 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__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[2];
- __shared__ float pad_temp_shared[336];
- __shared__ float kernel_shared[3072];
+ 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[14];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) / 112)) < 3) {
- pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x))] = (((((1 <= ((((int)blockIdx.x) % 7) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) / 7)) % 3))) && (((((int)blockIdx.x) % 7) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) / 7)) % 3)) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((((rc_outer [...]
- }
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 < 5; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 * 7) + (((int)threadIdx.x) >> 5)) < 32) {
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 3; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 * 672) + (((int)threadIdx.x) * 3)) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 * 64512)) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s * 3)) + rx_outer_outer)];
- }
- }
- }
- __syncthreads();
- for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
- for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 21) + (ry_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_inner * 3)) + ry_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 21) + (ry_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_inner * 3)) + ry_inner) + 1536)]));
- }
- }
+ 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;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = ((((((int)threadIdx.x) < 23) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 616) / 81) * 49)) + (((((int)threadIdx.x) + 49) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ }
+ }
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
- compute[(((((((int)blockIdx.x) / 7) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) / 7) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) + 1568)] = max((conv2d_nchw[1] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) / 7)) + 32)]), 0.000000e+00f);
}
@@ -539,7 +1650,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 33.234 seconds)
+ **Total running time of the script:** ( 2 minutes 38.971 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 774b5eb9b..03709b710 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
@@ -646,7 +646,7 @@ 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)
- 9.8089 9.8375 9.8414 9.7478 0.0432
+ 9.8854 9.8812 9.8988 9.8763 0.0096
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 d16e96435..f0a154f56 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
@@ -665,7 +665,7 @@ 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)
- 759.9897 759.5531 761.2447 759.1715 0.9009
+ 745.6005 745.6069 746.1523 745.0421 0.4533
@@ -693,7 +693,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.556 seconds)
+ **Total running time of the script:** ( 1 minutes 19.510 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 11ed3aea0..44ea9278e 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
@@ -396,19 +396,23 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [512], [])[((i.outer.inner*16) + j.init)] = 0f32
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*256) + (i.inner.init*16)) + j.init)] = 0f32
+ }
}
for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = ((i.outer.inner*16) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*256) + (i.inner*16)) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
}
}
}
@@ -471,7 +475,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 2.289 ms
+ Execution time of this operator: 1.661 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 fb938d471..55e3ad3bc 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
=================
-**00:43.318** total execution time for **how_to_tune_with_autotvm** files:
+**00:43.987** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.289 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.958 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.016 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.004 | 0.0 MB |
-+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_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 |
++--------------------------------------------------------------------------------------------------+-----------+--------+
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 a92afada3..a9042372f 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
@@ -879,8 +879,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 42.40/42.40 result: MeasureResult(costs=(0.0054599264210526315,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6463680267333984, timestamp=1656533855.9871092) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 110.46/110.46 result: MeasureResult(costs=(0.0020958639791666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.828981876373291, timestamp=1656541832.4940493) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1003,7 +1003,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,7 +1126,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,7 +1249,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/110.46 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
@@ -1267,7 +1267,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('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', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1390,7 +1390,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1513,7 +1513,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1636,7 +1636,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1759,7 +1759,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1882,7 +1882,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2005,7 +2005,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2128,7 +2128,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2251,7 +2251,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2339,7 +2339,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fcc6bfc2fa2
+ 12: 0x00007fb161115fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2404,7 +2404,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 143.88/143.88 result: MeasureResult(costs=(0.00160893531,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4241416454315186, timestamp=1656533882.6151175) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 142.44/142.44 result: MeasureResult(costs=(0.0016252628000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3169445991516113, timestamp=1656541858.9688838) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2461,7 +2461,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
- Time cost of this operator: 0.002009
+ Time cost of this operator: 0.001990
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 66df631ee..4fb1cf816 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
@@ -328,10 +328,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.639 (1, 2, 10, 10, 3) 2 1 [311.8]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.121 0.987 (1, 6, 10, 10) 1 1 [3.121]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.18 0.373 (1, 1, 10, 10, 3) 1 1 [1.18]
- Total_time - 316.101 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.1 98.701 (1, 2, 10, 10, 3) 2 1 [309.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.106 0.992 (1, 6, 10, 10) 1 1 [3.106]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.308 (1, 1, 10, 10, 3) 1 1 [0.963]
+ Total_time - 313.169 - - - - -
@@ -397,10 +397,10 @@ 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 80.562 96.629 (1, 6, 10, 10, 1) 2 1 [80.562]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.844 2.211 (1, 6, 10, 10) 1 1 [1.844]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 1.16 (1, 1, 10, 10, 3) 1 1 [0.967]
- Total_time - 83.373 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 152.2 98.242 (1, 6, 10, 10, 1) 2 1 [152.2]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.768 1.141 (1, 6, 10, 10) 1 1 [1.768]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.956 0.617 (1, 1, 10, 10, 3) 1 1 [0.956]
+ Total_time - 154.924 - - - - -
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 ee6fc9c61..2c00d5091 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
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp9bak8r59/images/random'
+ '/tmp/tmp4zkvdb3h/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp9bak8r59/images/target contains 8144 images
- /tmp/tmp9bak8r59/images/random contains 5000 images
+ /tmp/tmp4zkvdb3h/images/target contains 8144 images
+ /tmp/tmp4zkvdb3h/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 56s - loss: 0.2288 - accuracy: 0.9210 - val_loss: 0.1531 - val_accuracy: 0.9581
+ 328/328 - 55s - loss: 0.2280 - accuracy: 0.9221 - val_loss: 0.1282 - val_accuracy: 0.9596
Epoch 2/3
- 328/328 - 53s - loss: 0.0975 - accuracy: 0.9617 - val_loss: 0.1320 - val_accuracy: 0.9588
+ 328/328 - 52s - loss: 0.0972 - accuracy: 0.9661 - val_loss: 0.1109 - val_accuracy: 0.9671
Epoch 3/3
- 328/328 - 53s - loss: 0.0652 - accuracy: 0.9758 - val_loss: 0.1244 - val_accuracy: 0.9668
+ 328/328 - 52s - loss: 0.0659 - accuracy: 0.9754 - val_loss: 0.1274 - val_accuracy: 0.9585
- <keras.callbacks.History object at 0x7f8d83287210>
+ <keras.callbacks.History object at 0x7f363b3fdd10>
@@ -864,7 +864,7 @@ 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:** ( 9 minutes 44.227 seconds)
+ **Total running time of the script:** ( 8 minutes 37.672 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 24a430502..c8a16b66d 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
@@ -5,14 +5,14 @@
Computation times
=================
-**10:32.973** total execution time for **how_to_work_with_microtvm** files:
+**09:23.343** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 09:44.227 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 08:37.672 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:45.152 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.225 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.595 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.446 | 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 a04b80946..6ed054e77 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
@@ -5,12 +5,12 @@
Computation times
=================
-**00:11.613** total execution time for **how_to_work_with_relay** files:
+**00:11.279** total execution time for **how_to_work_with_relay** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.774 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.580 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.499 | 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 e67b5a3ad..143f0d306 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
@@ -259,7 +259,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f8cf57339e0>
+ <function my_cuda_math_rule at 0x7f363a7a0320>
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 eed82abe0..ea6c0557c 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:04.133** total execution time for **how_to_work_with_schedules** files:
+**00:04.050** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.944 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.903 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.938 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.944 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.542 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.521 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.531 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.509 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.101 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.098 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.038 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.034 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.026 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.013 | 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 ced55fa7a..440531cf1 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -346,7 +346,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpipwfxcf3/input0.cc'\nsource_filename = \"/tmp/tmpipwfxcf3/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 floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpko97_vs6/input0.cc'\nsource_filename = \"/tmp/tmpko97_vs6/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 floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
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 17728875e..f4e16461d 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
=================
-**00:21.449** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.532** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.442 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.525 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 670194af8..cff5d4223 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ 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 23.70s!
+ resnet18_v1 inference graph built in 22.10s!
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 0784681bc..7da9a6b97 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.29s!
+ yolov3-tiny inference graph built in 15.60s!
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 12243efa2..1ed498573 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
=================
-**01:32.467** total execution time for **topic_vta_tutorials_frontend** files:
+**01:29.889** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.469 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.748 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.998 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.141 | 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 bc7768b86..a400182ae 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
=================
-**00:03.239** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.179** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.839 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.807 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.400 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.372 | 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 7bf5d6c43..f4407497e 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
=================
-**00:00.744** total execution time for **topic_vta_tutorials** files:
+**00:00.681** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.402 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.366 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.342 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.315 | 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 b28035d12..0a73e060a 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -327,7 +327,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.244 ms
+ Execution time of this operator: 93.724 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 6ab7d48b4..cbfb24eb4 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -449,16 +449,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.16/10.16 result: MeasureResult(costs=(0.026421065800000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5566368103027344, timestamp=1656532580.1935494) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.12/10.16 result: MeasureResult(costs=(0.1265065522,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1720869541168213, timestamp=1656532582.38161) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.70/11.70 result: MeasureResult(costs=(0.0229397172,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.554443359375, timestamp=1656532583.4443007) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.85/11.70 result: MeasureResult(costs=(0.145172307,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4352757930755615, timestamp=1656532586.4698496) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.65/11.70 result: MeasureResult(costs=(0.0734990044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3180365562438965, timestamp=1656532588.4477537) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.70/11.70 result: MeasureResult(costs=(0.1578454402,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.686985492706299, timestamp=1656532591.1802802) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.70 result: MeasureResult(costs=(0.309819843,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0784971714019775, timestamp=1656532596.3024294) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.55/11.70 result: MeasureResult(costs=(0.0254460102,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.548879861831665, timestamp=1656532596.8743258) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.60/11.70 result: MeasureResult(costs=(0.16734202439999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7891955375671387, timestamp=1656532599.7862093) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.36/11.70 result: MeasureResult(costs=(0.11356567980000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9236400127410889, timestamp=1656532601.7674947) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.22/9.22 result: MeasureResult(costs=(0.0291259634,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5961494445800781, timestamp=1656540711.0033371) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.69/9.22 result: MeasureResult(costs=(0.0996186054,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7388560771942139, timestamp=1656540712.7610924) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.0228154048,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.555936336517334, timestamp=1656540713.8021886) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.73/11.77 result: MeasureResult(costs=(0.15525667840000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5837182998657227, timestamp=1656540716.4438019) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.63/11.77 result: MeasureResult(costs=(0.0740317612,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.320026159286499, timestamp=1656540717.8917458) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.83/11.77 result: MeasureResult(costs=(0.1463942162,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.460580587387085, timestamp=1656540720.907882) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.88/11.77 result: MeasureResult(costs=(0.3058933154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.007894992828369, timestamp=1656540726.478014) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.69/11.77 result: MeasureResult(costs=(0.0251161864,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5427765846252441, timestamp=1656540727.0397494) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.92/11.77 result: MeasureResult(costs=(0.1399018654,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3358640670776367, timestamp=1656540729.4955604) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.79/11.77 result: MeasureResult(costs=(0.09623221959999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6406621932983398, timestamp=1656540731.1964812) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 63c07a167..711497afa 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -314,7 +314,7 @@ standard deviation.
.. code-block:: none
- {'mean': 499.0021495500003, 'median': 499.1115282999999, 'std': 1.0006195570651975}
+ {'mean': 492.78407607999964, 'median': 492.77864389999877, 'std': 0.3889919310436313}
@@ -550,31 +550,31 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.34/ 17.34 GFLOPS | Progress: (4/20) | 6.40 s
[Task 1/25] Current/Best: 6.16/ 17.34 GFLOPS | Progress: (8/20) | 9.41 s
[Task 1/25] Current/Best: 11.48/ 22.63 GFLOPS | Progress: (12/20) | 11.87 s
[Task 1/25] Current/Best: 16.76/ 22.69 GFLOPS | Progress: (16/20) | 13.56 s
[Task 1/25] Current/Best: 11.60/ 23.86 GFLOPS | Progress: (20/20) | 15.32 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.25/ 12.95 GFLOPS | Progress: (4/20) | 3.84 s
[Task 2/25] Current/Best: 14.26/ 18.47 GFLOPS | Progress: (8/20) | 5.14 s
[Task 2/25] Current/Best: 21.26/ 21.26 GFLOPS | Progress: (12/20) | 6.46 s
[Task 2/25] Current/Best: 12.23/ 21.26 GFLOPS | Progress: (16/20) | 7.73 s
[Task 2/25] Current/Best: 18.96/ 21.26 GFLOPS | Progress: (20/20) | 9.35 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/ 10.55 GFLOPS | Progress: (4/20) | 5.91 s
[Task 3/25] Current/Best: 15.50/ 16.88 GFLOPS | Progress: (8/20) | 7.83 s
[Task 3/25] Current/Best: 14.88/ 16.88 GFLOPS | Progress: (12/20) | 9.55 s
[Task 3/25] Current/Best: 7.20/ 23.69 GFLOPS | Progress: (16/20) | 11.49 s
[Task 3/25] Current/Best: 12.49/ 23.69 GFLOPS | Progress: (20/20) | 16.05 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.22 GFLOPS | Progress: (4/20) | 2.41 s
[Task 4/25] Current/Best: 6.65/ 20.22 GFLOPS | Progress: (8/20) | 6.85 s
[Task 4/25] Current/Best: 21.60/ 21.60 GFLOPS | Progress: (12/20) | 11.54 s
[Task 4/25] Current/Best: 16.99/ 21.60 GFLOPS | Progress: (16/20) | 13.79 s
[Task 4/25] Current/Best: 13.13/ 21.60 GFLOPS | Progress: (20/20) | 15.72 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.48/ 10.13 GFLOPS | Progress: (4/20) | 2.61 s
[Task 5/25] Current/Best: 11.76/ 12.80 GFLOPS | Progress: (8/20) | 4.69 s
[Task 5/25] Current/Best: 9.70/ 17.99 GFLOPS | Progress: (12/20) | 7.85 s
[Task 5/25] Current/Best: 11.66/ 22.62 GFLOPS | Progress: (16/20) | 9.26 s
[Task 5/25] Current/Best: 11.96/ 22.62 GFLOPS | Progress: (20/20) | 11.16 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.26/ 20.74 GFLOPS | Progress: (4/20) | 4.00 s
[Task 6/25] Current/Best: 18.94/ 20.74 GFLOPS | Progress: (8/20) | 5.77 s
[Task 6/25] Current/Best: 13.20/ 20.74 GFLOPS | Progress: (12/20) | 7.70 s
[Task 6/25] Current/Best: 19.89/ 20.74 GFLOPS | Progress: (16/20) | 9.93 s
[Task 6/25] Current/Best: 3.72/ 20.74 GFLOPS | Progress: (20/20) | 12.48 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.25/ 12.85 GFLOPS | Progress: (4/20) | 3.61 s
[Task 7/25] Current/Best: 20.20/ 21.07 GFLOPS | Progress: (8/20) | 5.12 s
[Task 7/25] Current/Best: 15.82/ 21.07 GFLOPS | Progress: (12/20) | 7.05 s
[Task 7/25] Current/Best: 12.25/ 21.07 GFLOPS | Progress: (16/20) | 9.10 s
[Task 7/25] Current/Best: 6.33/ 21.71 GFLOPS | Progress: (20/20) | 11.57 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.18/ 14.08 GFLOPS | Progress: (4/20) | 2.91 s
[Task 8/25] Current/Best: 9.36/ 14.08 GFLOPS | Progress: (8/20) | 7.72 s
[Task 8/25] Current/Best: 12.92/ 14.08 GFLOPS | Progress: (12/20) | 13.95 s
[Task 8/25] Current/Best: 18.92/ 18.92 GFLOPS | Progress: (16/20) | 16.06 s
[Task 8/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (20/20) | 22.57 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.16/ 15.67 GFLOPS | Progress: (4/20) | 11.99 s
[Task 9/25] Current/Best: 22.44/ 22.44 GFLOPS | Progress: (8/20) | 13.77 s
[Task 9/25] Current/Best: 8.22/ 22.44 GFLOPS | Progress: (12/20) | 16.14 s
[Task 9/25] Current/Best: 17.54/ 22.44 GFLOPS | Progress: (16/20) | 18.82 s
[Task 9/25] Current/Best: 8.92/ 22.44 GFLOPS | Progress: (20/20) | 26.64 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/20) | 2.59 s
[Task 10/25] Current/Best: 15.44/ 18.14 GFLOPS | Progress: (8/20) | 4.17 s
[Task 10/25] Current/Best: 12.58/ 18.98 GFLOPS | Progress: (12/20) | 5.71 s
[Task 10/25] Current/Best: 19.12/ 20.36 GFLOPS | Progress: (16/20) | 6.83 s
[Task 10/25] Current/Best: 8.86/ 20.36 GFLOPS | Progress: (20/20
) | 8.39 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.32/ 18.01 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 16.03/ 18.01 GFLOPS | Progress: (8/20) | 6.05 s
[Task 11/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (12/20) | 8.11 s
[Task 11/25] Current/Best: 13.07/ 21.12 GFLOPS | Progress: (16/20) | 10.95 s
[Task 11/25] Current/Best: 19.35/ 21.50 GFLOPS | Progress: (20/20) | 13.00 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.65/ 18.11 GFLOPS | Progress: (4/20) | 5.46 s
[Task 12/25] Current/Best: 5.24/ 18.11 GFLOPS | Progress: (8/20) | 9.19 s
[Task 12/25] Current/Best: 19.06/ 19.06 GFLOPS | Progress: (12/20) | 11.20 s
[Task 12/25] Current/Best: 12.69/ 19.06 GFLOPS | Progress: (16/20) | 13.99 s
[Task 12/25] Current/Best: 15.23/ 19.06 GFLOPS | Progress: (20/20) | 15.90 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.85/ 17.18 GFLOPS | Progress: (4/20) | 3.70 s
[Task 13/25] Current/Best: 15.79/ 20.88 GFLOPS | Progress: (8/20) | 6.16 s
[Task 13/25] Current/Best: 19.08/ 21.25 GFLOPS | Progress: (12/20) | 9.09 s
[Task 13/25] Current/Best: 12.21/ 21.25 GFLOPS | Progress: (16/20) | 12.53 s
[Task 13/25] Current/Best: 18.61/ 21.25 GFLOPS | Progress: (20/20) | 14.79 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.57/ 13.57 GFLOPS | Progress: (4/20) | 3.36 s
[Task 14/25] Current/Best: 6.09/ 13.57 GFLOPS | Progress: (8/20) | 5.55 s
[Task 14/25] Current/Best: 21.15/ 21.15 GFLOPS | Progress: (12/20) | 8.09 s
[Task 14/25] Current/Best: 16.79/ 21.15 GFLOPS | Progress: (16/20) | 9.75 s Done.
-
[Task 14/25] Current/Best: 17.17/ 21.15 GFLOPS | Progress: (20/20) | 11.50 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.00/ 17.60 GFLOPS | Progress: (4/20) | 2.76 s
[Task 15/25] Current/Best: 14.42/ 17.96 GFLOPS | Progress: (8/20) | 4.10 s
[Task 15/25] Current/Best: 10.35/ 22.18 GFLOPS | Progress: (12/20) | 6.20 s
[Task 15/25] Current/Best: 20.36/ 22.18 GFLOPS | Progress: (16/20) | 9.20 s
[Task 15/25] Current/Best: 9.68/ 22.18 GFLOPS | Progress: (20/20) | 10.18 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (4/20) | 2.98 s
[Task 16/25] Current/Best: 3.00/ 20.86 GFLOPS | Progress: (8/20) | 4.62 s
[Task 16/25] Current/Best: 19.49/ 20.86 GFLOPS | Progress: (12/20) | 5.85 s
[Task 16/25] Current/Best: 17.43/ 20.86 GFLOPS | Progress: (16/20) |
7.23 s
[Task 16/25] Current/Best: 10.01/ 22.09 GFLOPS | Progress: (20/20) | 9.27 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.93/ 18.79 GFLOPS | Progress: (4/20) | 4.74 s
[Task 17/25] Current/Best: 14.20/ 22.88 GFLOPS | Progress: (8/20) | 7.63 s
[Task 17/25] Current/Best: 16.74/ 22.88 GFLOPS | Progress: (12/20) | 9.71 s
[Task 17/25] Current/Best: 16.49/ 22.88 GFLOPS | Progress: (16/20) | 11.88 s
[Task 17/25] Current/Best: 10.02/ 22.88 GFLOPS | Progress: (20/20) | 14.02 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.12/ 17.78 GFLOPS | Progress: (4/20) | 3.73 s
[Task 18/25] Current/Best: 10.57/ 18.38 GFLOPS | Progress: (8/20) | 7.25 s
[Task 18/25] Current/Best: 18.67/ 18.67 GFLOPS | Progress: (12/20) | 9.18 s
[Task 18/25] Current/Best: 9.94/ 18.67 GFLOPS | Progress: (16/20) | 12.81 s
[Task 18/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (20/20) | 14.33 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.90/ 20.08 GFLOPS | Progress: (4/20) | 6.12 s
[Task 19/25] Current/Best: 2.60/ 20.08 GFLOPS | Progress: (8/20) | 9.38 s
[Task 19/25] Current/Best: 19.42/ 21.10 GFLOPS | Progress: (12/20) | 12.15 s
[Task 19/25] Current/Best: 15.11/ 21.10 GFLOPS | Progress: (16/20) | 14.94 s
[Task 19/25] Current/Best: 2.69/ 23.17 GFLOPS | Progress: (20/20) | 17.72 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.78/ 14.84 GFLOPS | Progress: (4/20) | 3.36 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.54/ 17.54 GFLOPS | Progress: (4/20) | 6.20 s
[Task 1/25] Current/Best: 6.15/ 17.54 GFLOPS | Progress: (8/20) | 9.10 s
[Task 1/25] Current/Best: 11.55/ 22.76 GFLOPS | Progress: (12/20) | 11.51 s
[Task 1/25] Current/Best: 16.90/ 22.89 GFLOPS | Progress: (16/20) | 13.18 s
[Task 1/25] Current/Best: 11.63/ 22.89 GFLOPS | Progress: (20/20) | 14.92 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.25/ 12.86 GFLOPS | Progress: (4/20) | 3.78 s
[Task 2/25] Current/Best: 14.19/ 18.13 GFLOPS | Progress: (8/20) | 5.10 s
[Task 2/25] Current/Best: 21.08/ 21.08 GFLOPS | Progress: (12/20) | 6.41 s
[Task 2/25] Current/Best: 12.92/ 21.08 GFLOPS | Progress: (16/20) | 7.66 s
[Task 2/25] Current/Best: 19.80/ 21.08 GFLOPS | Progress: (20/20) | 9.25 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/ 10.50 GFLOPS | Progress: (4/20) | 5.85 s
[Task 3/25] Current/Best: 15.60/ 16.89 GFLOPS | Progress: (8/20) | 7.76 s
[Task 3/25] Current/Best: 14.91/ 16.89 GFLOPS | Progress: (12/20) | 9.48 s
[Task 3/25] Current/Best: 7.23/ 23.86 GFLOPS | Progress: (16/20) | 11.37 s
[Task 3/25] Current/Best: 12.60/ 23.86 GFLOPS | Progress: (20/20) | 15.88 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.48 GFLOPS | Progress: (4/20) | 2.36 s
[Task 4/25] Current/Best: 6.65/ 20.48 GFLOPS | Progress: (8/20) | 6.66 s
[Task 4/25] Current/Best: 21.95/ 21.95 GFLOPS | Progress: (12/20) | 11.15 s
[Task 4/25] Current/Best: 17.41/ 21.95 GFLOPS | Progress: (16/20) | 13.38 s
[Task 4/25] Current/Best: 13.17/ 21.95 GFLOPS | Progress: (20/20) | 15.38 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.94/ 10.40 GFLOPS | Progress: (4/20) | 2.57 s
[Task 5/25] Current/Best: 11.92/ 12.80 GFLOPS | Progress: (8/20) | 4.61 s
[Task 5/25] Current/Best: 11.38/ 18.13 GFLOPS | Progress: (12/20) | 7.66 s
[Task 5/25] Current/Best: 11.83/ 22.41 GFLOPS | Progress: (16/20) | 9.06 s
[Task 5/25] Current/Best: 12.01/ 22.41 GFLOPS | Progress: (20/20) | 10.87 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.21/ 20.78 GFLOPS | Progress: (4/20) | 3.92 s
[Task 6/25] Current/Best: 19.06/ 20.78 GFLOPS | Progress: (8/20) | 5.67 s
[Task 6/25] Current/Best: 13.11/ 20.78 GFLOPS | Progress: (12/20) | 7.58 s
[Task 6/25] Current/Best: 20.00/ 20.78 GFLOPS | Progress: (16/20) | 9.81 s
[Task 6/25] Current/Best: 3.74/ 20.78 GFLOPS | Progress: (20/20) | 12.34 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.20/ 12.82 GFLOPS | Progress: (4/20) | 3.59 s
[Task 7/25] Current/Best: 20.33/ 21.09 GFLOPS | Progress: (8/20) | 5.08 s
[Task 7/25] Current/Best: 16.17/ 21.09 GFLOPS | Progress: (12/20) | 6.97 s
[Task 7/25] Current/Best: 12.27/ 21.09 GFLOPS | Progress: (16/20) | 8.99 s
[Task 7/25] Current/Best: 6.41/ 21.86 GFLOPS | Progress: (20/20) | 11.43 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.13/ 13.91 GFLOPS | Progress: (4/20) | 2.90 s
[Task 8/25] Current/Best: 9.69/ 13.91 GFLOPS | Progress: (8/20) | 7.60 s
[Task 8/25] Current/Best: 12.69/ 13.91 GFLOPS | Progress: (12/20) | 13.65 s
[Task 8/25] Current/Best: 18.67/ 18.67 GFLOPS | Progress: (16/20) | 15.75 s
[Task 8/25] Current/Best: 19.88/ 19.88 GFLOPS | Progress: (20/20) | 22.15 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.36/ 15.82 GFLOPS | Progress: (4/20) | 11.95 s
[Task 9/25] Current/Best: 23.48/ 23.48 GFLOPS | Progress: (8/20) | 13.75 s
[Task 9/25] Current/Best: 8.26/ 23.48 GFLOPS | Progress: (12/20) | 16.05 s
[Task 9/25] Current/Best: 18.05/ 23.48 GFLOPS | Progress: (16/20) | 18.68 s
[Task 9/25] Current/Best: 9.01/ 23.48 GFLOPS | Progress: (20/20) | 26.16 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.12/ 18.12 GFLOPS | Progress: (4/20) | 2.55 s
[Task 10/25] Current/Best: 15.55/ 18.12 GFLOPS | Progress: (8/20) | 4.18 s
[Task 10/25] Current/Best: 12.79/ 19.03 GFLOPS | Progress: (12/20) | 5.69 s
[Task 10/25] Current/Best: 19.07/ 20.36 GFLOPS | Progress: (16/20) | 6.80 s
[Task 10/25] Current/Best: 8.79/ 20.36 GFLOPS | Progress: (20/20
) | 8.34 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.26/ 18.15 GFLOPS | Progress: (4/20) | 3.31 s
[Task 11/25] Current/Best: 16.93/ 18.15 GFLOPS | Progress: (8/20) | 6.04 s
[Task 11/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (12/20) | 8.10 s
[Task 11/25] Current/Best: 13.40/ 21.22 GFLOPS | Progress: (16/20) | 10.86 s
[Task 11/25] Current/Best: 19.48/ 21.60 GFLOPS | Progress: (20/20) | 12.87 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.82/ 18.15 GFLOPS | Progress: (4/20) | 5.24 s
[Task 12/25] Current/Best: 5.30/ 18.15 GFLOPS | Progress: (8/20) | 8.87 s
[Task 12/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (12/20) | 10.83 s
[Task 12/25] Current/Best: 15.62/ 18.95 GFLOPS | Progress: (16/20) | 13.59 s
[Task 12/25] Current/Best: 15.13/ 19.08 GFLOPS | Progress: (20/20) | 15.51 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.59/ 17.35 GFLOPS | Progress: (4/20) | 3.68 s
[Task 13/25] Current/Best: 16.15/ 21.04 GFLOPS | Progress: (8/20) | 6.07 s
[Task 13/25] Current/Best: 19.54/ 21.04 GFLOPS | Progress: (12/20) | 8.98 s
[Task 13/25] Current/Best: 12.24/ 21.04 GFLOPS | Progress: (16/20) | 12.40 s
[Task 13/25] Current/Best: 18.79/ 21.04 GFLOPS | Progress: (20/20) | 14.62 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.57/ 13.57 GFLOPS | Progress: (4/20) | 3.33 s
[Task 14/25] Current/Best: 6.11/ 13.57 GFLOPS | Progress: (8/20) | 5.52 s
[Task 14/25] Current/Best: 21.12/ 21.12 GFLOPS | Progress: (12/20) | 8.03 s
[Task 14/25] Current/Best: 17.28/ 21.12 GFLOPS | Progress: (16/20) | 9.68 s Done.
+
[Task 14/25] Current/Best: 17.07/ 21.12 GFLOPS | Progress: (20/20) | 11.40 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.17/ 17.68 GFLOPS | Progress: (4/20) | 2.71 s
[Task 15/25] Current/Best: 14.52/ 18.06 GFLOPS | Progress: (8/20) | 4.05 s
[Task 15/25] Current/Best: 10.38/ 22.33 GFLOPS | Progress: (12/20) | 6.11 s
[Task 15/25] Current/Best: 20.37/ 22.33 GFLOPS | Progress: (16/20) | 8.97 s
[Task 15/25] Current/Best: 9.72/ 22.33 GFLOPS | Progress: (20/20) | 9.94 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (4/20) | 2.95 s
[Task 16/25] Current/Best: 3.04/ 20.66 GFLOPS | Progress: (8/20) | 4.56 s
[Task 16/25] Current/Best: 19.49/ 20.66 GFLOPS | Progress: (12/20) | 5.78 s
[Task 16/25] Current/Best: 17.72/ 20.66 GFLOPS | Progress: (16/20) |
7.11 s
[Task 16/25] Current/Best: 10.05/ 21.97 GFLOPS | Progress: (20/20) | 9.14 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.09/ 18.45 GFLOPS | Progress: (4/20) | 4.72 s
[Task 17/25] Current/Best: 14.41/ 23.34 GFLOPS | Progress: (8/20) | 7.57 s
[Task 17/25] Current/Best: 16.81/ 23.34 GFLOPS | Progress: (12/20) | 9.61 s
[Task 17/25] Current/Best: 16.55/ 23.34 GFLOPS | Progress: (16/20) | 11.72 s
[Task 17/25] Current/Best: 10.05/ 23.34 GFLOPS | Progress: (20/20) | 13.82 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.03/ 17.81 GFLOPS | Progress: (4/20) | 3.63 s
[Task 18/25] Current/Best: 10.61/ 17.84 GFLOPS | Progress: (8/20) | 7.03 s
[Task 18/25] Current/Best: 19.30/ 19.30 GFLOPS | Progress: (12/20) | 8.94 s
[Task 18/25] Current/Best: 10.05/ 19.30 GFLOPS | Progress: (16/20) | 12.46 s
[Task 18/25] Current/Best: 20.87/ 20.87 GFLOPS | Progress: (20/20) | 13.98 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.93/ 20.34 GFLOPS | Progress: (4/20) | 6.01 s
[Task 19/25] Current/Best: 2.60/ 20.34 GFLOPS | Progress: (8/20) | 9.26 s
[Task 19/25] Current/Best: 20.24/ 21.57 GFLOPS | Progress: (12/20) | 12.03 s
[Task 19/25] Current/Best: 15.50/ 21.57 GFLOPS | Progress: (16/20) | 14.82 s
[Task 19/25] Current/Best: 2.70/ 23.70 GFLOPS | Progress: (20/20) | 17.61 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.22/ 15.15 GFLOPS | Progress: (4/20) | 3.27 s Done.
Done.
-
[Task 20/25] Current/Best: 10.27/ 14.84 GFLOPS | Progress: (8/20) | 6.82 s
[Task 20/25] Current/Best: 2.32/ 16.51 GFLOPS | Progress: (12/20) | 10.78 s
[Task 20/25] Current/Best: 12.50/ 16.51 GFLOPS | Progress: (16/20) | 14.41 s
[Task 20/25] Current/Best: 13.36/ 21.60 GFLOPS | Progress: (20/20) | 16.49 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.72 GFLOPS | Progress: (4/20) | 3.26 s
[Task 21/25] Current/Best: 14.39/ 17.72 GFLOPS | Progress: (8/20) | 4.83 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 6.99 s
[Task 21/25] Current/Best: 18.04/ 18.04 GFLOPS | Progress: (16/20) | 10.45 s
[Task 21/25] Current/Best: 4.47/ 18.04 GFLOPS | Progress: (20/20) | 17.64 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.94 GFLOPS | Progress: (4/20
) | 2.74 s
[Task 22/25] Current/Best: 9.18/ 21.23 GFLOPS | Progress: (8/20) | 4.65 s
[Task 22/25] Current/Best: 19.44/ 21.23 GFLOPS | Progress: (12/20) | 6.96 s
[Task 22/25] Current/Best: 15.20/ 21.23 GFLOPS | Progress: (16/20) | 9.01 s
[Task 22/25] Current/Best: 14.76/ 21.23 GFLOPS | Progress: (20/20) | 10.73 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.42/ 20.24 GFLOPS | Progress: (4/20) | 3.26 s
[Task 23/25] Current/Best: 15.45/ 20.24 GFLOPS | Progress: (8/20) | 6.63 s
[Task 23/25] Current/Best: 20.69/ 21.26 GFLOPS | Progress: (12/20) | 8.46 s
[Task 23/25] Current/Best: 5.92/ 21.26 GFLOPS | Progress: (16/20) | 15.72 s
[Task 23/25] Current/Best: 7.48/ 21.26 GFLOPS | Progress: (20/20) | 19.99 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.33/ 8.33 GFLOPS | Progress: (4/20) | 11.84 s
[Task 24/25] Current/Best: 1.96/ 8.33 GFLOPS | Progress: (8/20) | 22.90 s
[Task 24/25] Current/Best: 3.89/ 8.33 GFLOPS | Progress: (12/20) | 34.48 s Done.
+
[Task 20/25] Current/Best: 9.43/ 15.15 GFLOPS | Progress: (8/20) | 6.54 s
[Task 20/25] Current/Best: 2.32/ 16.15 GFLOPS | Progress: (12/20) | 10.44 s
[Task 20/25] Current/Best: 12.41/ 16.15 GFLOPS | Progress: (16/20) | 14.08 s
[Task 20/25] Current/Best: 13.22/ 22.22 GFLOPS | Progress: (20/20) | 16.15 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.60 GFLOPS | Progress: (4/20) | 3.19 s
[Task 21/25] Current/Best: 14.66/ 17.60 GFLOPS | Progress: (8/20) | 4.75 s
[Task 21/25] Current/Best: 1.61/ 17.60 GFLOPS | Progress: (12/20) | 6.90 s
[Task 21/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (16/20) | 10.34 s
[Task 21/25] Current/Best: 4.47/ 18.18 GFLOPS | Progress: (20/20) | 17.28 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.05 GFLOPS | Progress: (4/20
) | 2.65 s
[Task 22/25] Current/Best: 8.62/ 22.01 GFLOPS | Progress: (8/20) | 4.62 s
[Task 22/25] Current/Best: 19.89/ 22.01 GFLOPS | Progress: (12/20) | 6.93 s
[Task 22/25] Current/Best: 15.45/ 22.01 GFLOPS | Progress: (16/20) | 9.00 s
[Task 22/25] Current/Best: 14.34/ 22.01 GFLOPS | Progress: (20/20) | 10.70 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.33/ 20.68 GFLOPS | Progress: (4/20) | 3.24 s
[Task 23/25] Current/Best: 14.79/ 20.68 GFLOPS | Progress: (8/20) | 6.50 s
[Task 23/25] Current/Best: 20.87/ 21.86 GFLOPS | Progress: (12/20) | 8.28 s
[Task 23/25] Current/Best: 6.39/ 21.86 GFLOPS | Progress: (16/20) | 15.20 s
[Task 23/25] Current/Best: 8.01/ 21.86 GFLOPS | Progress: (20/20) | 19.37 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.26/ 8.26 GFLOPS | Progress: (4/20) | 11.78 s
[Task 24/25] Current/Best: 3.76/ 8.26 GFLOPS | Progress: (8/20) | 23.01 s
[Task 24/25] Current/Best: 4.68/ 8.26 GFLOPS | Progress: (12/20) | 33.72 s Done.
Done.
-
[Task 24/25] Current/Best: 7.35/ 8.45 GFLOPS | Progress: (16/20) | 40.11 s
[Task 24/25] Current/Best: 3.24/ 8.86 GFLOPS | Progress: (20/20) | 46.17 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 2.89 GFLOPS | Progress: (4/20) | 11.61 s
[Task 25/25] Current/Best: 5.50/ 7.52 GFLOPS | Progress: (8/20) | 22.90 s
[Task 25/25] Current/Best: 5.84/ 7.52 GFLOPS | Progress: (12/20) | 34.33 s
[Task 25/25] Current/Best: 5.72/ 8.59 GFLOPS | Progress: (16/20) | 36.08 s
[Task 25/25] Current/Best: 2.92/ 8.72 GFLOPS | Progress: (20/20) | 46.77 s
+
[Task 24/25] Current/Best: 6.28/ 9.30 GFLOPS | Progress: (16/20) | 39.11 s
[Task 24/25] Current/Best: 3.44/ 9.30 GFLOPS | Progress: (20/20) | 44.89 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.76 GFLOPS | Progress: (4/20) | 11.54 s
[Task 25/25] Current/Best: 6.09/ 8.20 GFLOPS | Progress: (8/20) | 22.82 s
[Task 25/25] Current/Best: 6.01/ 8.20 GFLOPS | Progress: (12/20) | 34.27 s
[Task 25/25] Current/Best: 5.87/ 8.92 GFLOPS | Progress: (16/20) | 36.10 s
[Task 25/25] Current/Best: 2.88/ 8.92 GFLOPS | Progress: (20/20) | 46.79 s
@@ -735,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 414.98069430999976, 'median': 414.51188045000436, 'std': 1.4534486988092654}
- unoptimized: {'mean': 499.0021495500003, 'median': 499.1115282999999, 'std': 1.0006195570651975}
+ optimized: {'mean': 411.4486063499976, 'median': 411.3848237999946, 'std': 0.7223690858981291}
+ unoptimized: {'mean': 492.78407607999964, 'median': 492.77864389999877, 'std': 0.3889919310436313}
@@ -759,7 +759,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 18.790 seconds)
+ **Total running time of the script:** ( 10 minutes 8.755 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 8465384bb..06aa034a8 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -269,7 +269,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.299e-07 secs/op
+ 1.214e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index c7dc551bf..4d4c461c8 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -262,7 +262,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x22804930)), stage(b, placeholder(b, 0x27bfddf0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x20829460)), stage(b, placeholder(b, 0x8bce2c0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 9b06d01b4..81bedd095 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,24 +5,24 @@
Computation times
=================
-**13:03.333** total execution time for **tutorial** files:
+**12:50.374** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:18.790 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:08.755 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.459 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.691 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:46.433 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:49.520 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:28.661 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:27.780 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.103 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.644 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.030 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.152 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.701 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.682 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.155 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.150 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.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 295e350e4..a70837e32 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -390,7 +390,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000006
+ parallel: 0.000007
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.161719999861817e-06 1.0
- naive 6.683999999999999e-06 0.8189450263073426
- parallel 6.0326e-06 0.739133417968533
- vector 2.4601700000000002e-05 3.0142788530379043
+ numpy 8.196840001346573e-06 1.0
+ naive 6.6586999999999995e-06 0.8123496370438013
+ parallel 6.944500000000001e-06 0.8472167321625361
+ vector 2.4564900000000003e-05 2.996874404766287
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019125
+ Numpy running time: 0.018701
@@ -983,7 +983,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.489482
+ none: 3.240231
@@ -1088,7 +1088,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.322924
+ blocking: 0.303960
@@ -1186,7 +1186,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.344663
+ vectorization: 0.339425
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1262,7 +1262,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.127887
+ loop permutation: 0.116881
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1363,7 +1363,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.110899
+ array packing: 0.109708
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1458,7 +1458,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.113089
+ block caching: 0.110648
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1546,7 +1546,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.146494
+ parallelization: 0.144626
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1627,13 +1627,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4894820561000004 1.0
- blocking 0.32292440769999997 0.09254221758655913
- vectorization 0.3446631945 0.09877202087842539
- loop permutation 0.127887387 0.03664938949218515
- array packing 0.1108994951 0.03178107619328072
- block caching 0.11308885370000002 0.03240849268799311
- parallelization 0.1464942655 0.04198166465533526
+ none 3.2402305365000004 1.0
+ blocking 0.303959731 0.09380805704285726
+ vectorization 0.33942504900000003 0.10475336405126184
+ loop permutation 0.11688146609999998 0.03607195993722466
+ array packing 0.10970802340000001 0.03385809193641614
+ block caching 0.11064753860000001 0.034148045132467074
+ parallelization 0.14462649519999998 0.04463463126183027
@@ -1673,11 +1673,6 @@ 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 2.459 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 09722f01a..c3a010ce2 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-84c66da617e12c6690de064c09bf242f4a095dfc
+b552bcf1d0584a8ba64915be2efa7daf8907b8e3
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index bdf5f0279..a9adbf2bf 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -422,7 +422,7 @@ to download the full example code</p>
<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.zipad583a90-6d99-428d-a92a-b5517dfddab7 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.zipf338fb74-416f-4c38-a80a-c5adf8387794 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 2fab24464..85d86508f 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -427,45 +427,46 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<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]
- 0%| | 16.0k/41.5M [00:00<08:11, 88.5kB/s]
- 0%| | 48.0k/41.5M [00:00<05:10, 140kB/s]
- 0%| | 96.0k/41.5M [00:00<03:40, 197kB/s]
- 0%| | 208k/41.5M [00:00<01:59, 362kB/s]
- 1%|1 | 432k/41.5M [00:00<01:03, 676kB/s]
- 2%|2 | 872k/41.5M [00:01<00:33, 1.27MB/s]
- 4%|4 | 1.72M/41.5M [00:01<00:17, 2.45MB/s]
- 8%|7 | 3.20M/41.5M [00:01<00:09, 4.32MB/s]
- 11%|#1 | 4.67M/41.5M [00:01<00:06, 5.57MB/s]
- 15%|#4 | 6.15M/41.5M [00:01<00:05, 6.42MB/s]
- 18%|#8 | 7.62M/41.5M [00:02<00:05, 7.00MB/s]
- 22%|##1 | 9.10M/41.5M [00:02<00:04, 7.40MB/s]
- 25%|##5 | 10.6M/41.5M [00:02<00:04, 7.68MB/s]
- 29%|##9 | 12.1M/41.5M [00:02<00:03, 7.87MB/s]
- 33%|###2 | 13.5M/41.5M [00:02<00:03, 8.01MB/s]
- 36%|###6 | 15.0M/41.5M [00:02<00:03, 8.11MB/s]
- 40%|###9 | 16.5M/41.5M [00:03<00:03, 8.17MB/s]
- 43%|####3 | 18.0M/41.5M [00:03<00:03, 8.19MB/s]
- 47%|####6 | 19.4M/41.5M [00:03<00:02, 9.44MB/s]
- 49%|####9 | 20.4M/41.5M [00:03<00:02, 9.54MB/s]
- 51%|#####1 | 21.4M/41.5M [00:03<00:02, 8.37MB/s]
- 54%|#####3 | 22.4M/41.5M [00:03<00:02, 7.53MB/s]
- 58%|#####7 | 23.9M/41.5M [00:04<00:02, 7.79MB/s]
- 61%|######1 | 25.3M/41.5M [00:04<00:02, 7.96MB/s]
- 65%|######4 | 26.8M/41.5M [00:04<00:01, 8.43MB/s]
- 68%|######8 | 28.3M/41.5M [00:04<00:01, 9.70MB/s]
- 71%|####### | 29.3M/41.5M [00:04<00:01, 8.92MB/s]
- 73%|#######2 | 30.2M/41.5M [00:04<00:01, 8.18MB/s]
- 75%|#######4 | 31.0M/41.5M [00:05<00:01, 6.86MB/s]
- 77%|#######6 | 31.8M/41.5M [00:05<00:01, 6.15MB/s]
- 78%|#######8 | 32.6M/41.5M [00:05<00:01, 5.54MB/s]
- 82%|########1 | 34.0M/41.5M [00:05<00:01, 6.38MB/s]
- 85%|########4 | 35.2M/41.5M [00:05<00:01, 6.51MB/s]
- 88%|########8 | 36.7M/41.5M [00:05<00:00, 7.05MB/s]
- 90%|######### | 37.4M/41.5M [00:06<00:00, 6.03MB/s]
- 93%|#########3| 38.8M/41.5M [00:06<00:00, 6.60MB/s]
- 96%|#########5| 39.6M/41.5M [00:06<00:00, 6.10MB/s]
- 99%|#########9| 41.1M/41.5M [00:06<00:00, 6.76MB/s]
-100%|##########| 41.5M/41.5M [00:06<00:00, 6.48MB/s]
+ 0%| | 16.0k/41.5M [00:00<08:05, 89.5kB/s]
+ 0%| | 40.0k/41.5M [00:00<06:16, 116kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:31, 205kB/s]
+ 0%| | 160k/41.5M [00:00<02:43, 265kB/s]
+ 1%| | 272k/41.5M [00:00<01:49, 394kB/s]
+ 1%|1 | 560k/41.5M [00:01<00:53, 805kB/s]
+ 2%|2 | 864k/41.5M [00:01<00:38, 1.10MB/s]
+ 4%|3 | 1.63M/41.5M [00:01<00:19, 2.18MB/s]
+ 7%|7 | 3.11M/41.5M [00:01<00:09, 4.13MB/s]
+ 11%|# | 4.55M/41.5M [00:01<00:07, 5.38MB/s]
+ 15%|#4 | 6.02M/41.5M [00:02<00:05, 6.31MB/s]
+ 18%|#8 | 7.50M/41.5M [00:02<00:05, 6.95MB/s]
+ 22%|##1 | 8.98M/41.5M [00:02<00:04, 7.39MB/s]
+ 25%|##5 | 10.5M/41.5M [00:02<00:04, 7.66MB/s]
+ 29%|##8 | 11.9M/41.5M [00:02<00:03, 8.93MB/s]
+ 32%|###2 | 13.3M/41.5M [00:02<00:02, 10.0MB/s]
+ 35%|###4 | 14.4M/41.5M [00:02<00:03, 9.08MB/s]
+ 37%|###6 | 15.3M/41.5M [00:03<00:03, 7.81MB/s]
+ 39%|###9 | 16.4M/41.5M [00:03<00:03, 7.25MB/s]
+ 43%|####2 | 17.8M/41.5M [00:03<00:03, 7.64MB/s]
+ 47%|####6 | 19.3M/41.5M [00:03<00:02, 7.89MB/s]
+ 50%|##### | 20.8M/41.5M [00:03<00:02, 8.06MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:04<00:02, 8.17MB/s]
+ 57%|#####7 | 23.7M/41.5M [00:04<00:02, 9.24MB/s]
+ 61%|###### | 25.1M/41.5M [00:04<00:01, 10.3MB/s]
+ 63%|######3 | 26.2M/41.5M [00:04<00:01, 9.31MB/s]
+ 65%|######5 | 27.2M/41.5M [00:04<00:01, 8.01MB/s]
+ 68%|######7 | 28.2M/41.5M [00:04<00:01, 8.33MB/s]
+ 71%|#######1 | 29.6M/41.5M [00:04<00:01, 9.73MB/s]
+ 74%|#######3 | 30.6M/41.5M [00:04<00:01, 8.71MB/s]
+ 76%|#######5 | 31.5M/41.5M [00:05<00:01, 7.44MB/s]
+ 78%|#######8 | 32.5M/41.5M [00:05<00:01, 8.12MB/s]
+ 82%|########1 | 34.0M/41.5M [00:05<00:00, 9.68MB/s]
+ 84%|########4 | 35.0M/41.5M [00:05<00:00, 8.66MB/s]
+ 87%|########6 | 35.9M/41.5M [00:05<00:00, 7.43MB/s]
+ 89%|########9 | 37.0M/41.5M [00:05<00:00, 7.06MB/s]
+ 93%|#########2| 38.4M/41.5M [00:06<00:00, 7.51MB/s]
+ 96%|#########6| 39.9M/41.5M [00:06<00:00, 7.79MB/s]
+100%|#########9| 41.4M/41.5M [00:06<00:00, 7.97MB/s]
+100%|##########| 41.5M/41.5M [00:06<00:00, 6.75MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 539d3ad8d..84359fbc7 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -488,7 +488,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 33.147 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.314 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.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_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 9194e183d..25238755b 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -409,9 +409,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 37%|###7 | 16.7M/44.7M [00:00<00:00, 175MB/s]
- 90%|########9 | 40.1M/44.7M [00:00<00:00, 217MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 214MB/s]
+ 39%|###9 | 17.5M/44.7M [00:00<00:00, 184MB/s]
+ 93%|#########2| 41.5M/44.7M [00:00<00:00, 224MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 220MB/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 ed71ca353..a14b1c153 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -631,7 +631,6 @@ 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 1.396 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 8f1c1eb93..0d71a822d 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>05:50.529</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:40.801</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,43 +331,43 @@
</colgroup>
<tbody>
<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>01:33.147</p></td>
+<td><p>01:10.314</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>01:01.396</p></td>
+<td><p>00:59.945</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:57.265</p></td>
+<td><p>00:56.420</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>00:32.869</p></td>
+<tr class="row-even"><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>00:42.625</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>00:24.353</p></td>
+<tr class="row-odd"><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>00:31.791</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:23.098</p></td>
+<td><p>00:22.901</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.846</p></td>
+<td><p>00:21.577</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>00:18.997</p></td>
+<td><p>00:18.875</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>00:14.286</p></td>
+<td><p>00:13.843</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>00:02.271</p></td>
+<td><p>00:02.511</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
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 160cc98fb..2fdc76273 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -648,7 +648,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3903 16.4060 16.5603 16.2809 0.0777
+ 16.3799 16.6577 16.9003 15.6369 0.4636
</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 f9f9b7ada..609f2f117 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -431,16 +431,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
- 3%|3 | 5.35M/170M [00:00<00:03, 56.1MB/s]
- 6%|6 | 10.7M/170M [00:00<00:03, 55.2MB/s]
- 20%|## | 34.3M/170M [00:00<00:00, 142MB/s]
- 33%|###2 | 55.8M/170M [00:00<00:00, 175MB/s]
- 46%|####5 | 77.3M/170M [00:00<00:00, 193MB/s]
- 59%|#####8 | 100M/170M [00:00<00:00, 208MB/s]
- 71%|#######1 | 121M/170M [00:00<00:00, 212MB/s]
- 84%|########4 | 143M/170M [00:00<00:00, 217MB/s]
- 97%|#########6| 165M/170M [00:00<00:00, 221MB/s]
-100%|##########| 170M/170M [00:00<00:00, 193MB/s]
+ 2%|2 | 4.03M/170M [00:00<00:04, 42.2MB/s]
+ 5%|5 | 8.75M/170M [00:00<00:03, 46.5MB/s]
+ 20%|## | 34.1M/170M [00:00<00:00, 147MB/s]
+ 36%|###6 | 61.7M/170M [00:00<00:00, 203MB/s]
+ 53%|#####2 | 90.0M/170M [00:00<00:00, 237MB/s]
+ 70%|######9 | 118M/170M [00:00<00:00, 257MB/s]
+ 86%|########6 | 146M/170M [00:00<00:00, 269MB/s]
+100%|##########| 170M/170M [00:00<00:00, 225MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: 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)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: 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').
@@ -535,7 +533,7 @@ 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 4.111 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 51.314 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 f90cb7cc4..845a23a60 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -472,7 +472,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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]
-100%|##########| 13.6M/13.6M [00:00<00:00, 181MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 186MB/s]
</pre></div>
</div>
</div>
@@ -561,7 +561,7 @@ 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)
- 90.4675 90.3879 95.3678 90.1745 0.5082
+ 90.3545 90.2167 95.0284 90.0519 0.6304
</pre></div>
</div>
<div class="admonition note">
@@ -600,7 +600,7 @@ 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 8.767 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.868 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 a78a17479..2ddc04504 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -565,7 +565,7 @@ 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)
- 119.2313 119.0809 126.9910 118.1904 0.9721
+ 119.0591 119.0262 124.0607 118.4468 0.5675
</pre></div>
</div>
<div class="admonition note">
@@ -593,7 +593,7 @@ 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> ( 1 minutes 59.088 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 49.711 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 765d81f6f..071026ced 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -504,7 +504,7 @@ 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> ( 3 minutes 2.257 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.787 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 afd2a266e..0f17fb268 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -436,24 +436,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6354/132723 [00:00<00:01, 63533.85KB/s]
- 11%|# | 14220/132723 [00:00<00:01, 72426.09KB/s]
- 16%|#6 | 21463/132723 [00:00<00:01, 69848.05KB/s]
- 22%|##2 | 29416/132723 [00:00<00:01, 73585.20KB/s]
- 28%|##7 | 36790/132723 [00:00<00:01, 68170.99KB/s]
- 34%|###3 | 44723/132723 [00:00<00:01, 71738.02KB/s]
- 40%|###9 | 52641/132723 [00:00<00:01, 74070.58KB/s]
- 46%|####5 | 60507/132723 [00:00<00:00, 75483.29KB/s]
- 51%|#####1 | 68097/132723 [00:00<00:00, 73977.71KB/s]
- 57%|#####7 | 76033/132723 [00:01<00:00, 75589.90KB/s]
- 63%|######3 | 84021/132723 [00:01<00:00, 76873.51KB/s]
- 69%|######9 | 91978/132723 [00:01<00:00, 77680.77KB/s]
- 75%|#######5 | 99941/132723 [00:01<00:00, 78263.85KB/s]
- 81%|########1 | 107994/132723 [00:01<00:00, 78939.85KB/s]
- 87%|########7 | 115953/132723 [00:01<00:00, 79132.07KB/s]
- 93%|#########3| 123873/132723 [00:01<00:00, 79034.73KB/s]
- 99%|#########9| 131857/132723 [00:01<00:00, 79272.95KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75813.81KB/s]
+ 5%|4 | 6580/132723 [00:00<00:01, 65794.26KB/s]
+ 12%|#1 | 15390/132723 [00:00<00:01, 78911.09KB/s]
+ 18%|#8 | 24210/132723 [00:00<00:01, 83148.01KB/s]
+ 25%|##4 | 32892/132723 [00:00<00:01, 84594.04KB/s]
+ 31%|###1 | 41681/132723 [00:00<00:01, 85777.15KB/s]
+ 38%|###8 | 50491/132723 [00:00<00:00, 86563.24KB/s]
+ 45%|####4 | 59324/132723 [00:00<00:00, 87138.71KB/s]
+ 51%|#####1 | 68190/132723 [00:00<00:00, 87620.94KB/s]
+ 58%|#####8 | 77068/132723 [00:00<00:00, 87979.87KB/s]
+ 65%|######4 | 85941/132723 [00:01<00:00, 88203.54KB/s]
+ 71%|#######1 | 94762/132723 [00:01<00:00, 88085.04KB/s]
+ 78%|#######8 | 103598/132723 [00:01<00:00, 88167.03KB/s]
+ 85%|########4 | 112425/132723 [00:01<00:00, 88195.43KB/s]
+ 91%|#########1| 121270/132723 [00:01<00:00, 88270.27KB/s]
+ 98%|#########8| 130098/132723 [00:01<00:00, 88073.42KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 86589.14KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -496,7 +494,7 @@ 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> ( 2 minutes 24.225 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> ( 2 minutes 18.923 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 e18873670..8a9806c0f 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>12:30.837</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:08.823</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -331,31 +331,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><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>03:04.111</p></td>
+<td><p>02:51.314</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>03:02.257</p></td>
+<tr class="row-even"><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>02:18.923</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<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>02:24.225</p></td>
+<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>01:49.711</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><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>01:59.088</p></td>
+<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>01:11.787</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>01:08.767</p></td>
+<td><p>01:05.868</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:29.962</p></td>
+<td><p>00:29.643</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>00:22.421</p></td>
+<td><p>00:21.571</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 ce7b28fe5..028516e00 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -604,7 +604,7 @@ 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.zipadf2beb8-5c45-44a9-b453-b3f610067637 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.zip82f61d30-ca3b-4b66-93ec-9f9a9e681d9d 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 73a9da5b1..5f8e13ca0 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:41.230</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:39.554</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,15 +331,15 @@
</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>00:37.965</p></td>
+<td><p>00:36.434</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>00:02.306</p></td>
+<td><p>00:02.200</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>00:00.953</p></td>
+<td><p>00:00.914</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 9221bfb1b..fbc41e597 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -507,10 +507,10 @@ 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: 6835us [6835us] (45.24%; 45.24%)
-FoldScaleAxis: 8272us [7us] (54.76%; 54.76%)
- FoldConstant: 8265us [1591us] (54.71%; 99.91%)
- InferType: 6674us [6674us] (44.18%; 80.75%)
+InferType: 6757us [6757us] (45.59%; 45.59%)
+FoldScaleAxis: 8064us [5us] (54.41%; 54.41%)
+ FoldConstant: 8059us [1611us] (54.37%; 99.93%)
+ InferType: 6447us [6447us] (43.50%; 80.00%)
</pre></div>
</div>
</div>
@@ -532,10 +532,10 @@ 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: 6471us [6471us] (44.77%; 44.77%)
-FoldScaleAxis: 7983us [6us] (55.23%; 55.23%)
- FoldConstant: 7977us [1647us] (55.19%; 99.93%)
- InferType: 6330us [6330us] (43.79%; 79.35%)
+InferType: 6419us [6419us] (44.87%; 44.87%)
+FoldScaleAxis: 7888us [5us] (55.13%; 55.13%)
+ FoldConstant: 7883us [1605us] (55.10%; 99.94%)
+ InferType: 6278us [6278us] (43.88%; 79.64%)
</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 486f6fc5c..6d9823d2a 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -556,7 +556,7 @@ 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: 37.193923 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.147502 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 aabfb3bd2..4efdd98f4 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -898,7 +898,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 13.388187 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.160906 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 65cc58a91..9862f42b9 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -453,8 +453,8 @@ 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: 0.019161
-Baseline: 3.514780
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018037
+Baseline: 3.192306
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -514,7 +514,7 @@ 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: 0.316769
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.302333
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -581,7 +581,7 @@ 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: 0.346321
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332278
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -642,7 +642,7 @@ 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: 0.133215
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117405
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -725,7 +725,7 @@ 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: 0.111473
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111784
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -811,7 +811,7 @@ 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: 0.111385
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111186
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -901,7 +901,7 @@ write to C when all the block results are ready.</p>
<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: 0.146088
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145332
</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 a0e488d03..b067734ee 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:35.506</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:33.713</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</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>00:33.099</p></td>
+<td><p>00:31.464</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="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>00:01.377</p></td>
+<td><p>00:01.246</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>00:01.029</p></td>
+<td><p>00:01.003</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 f36318543..972b0f64c 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>05:13.679</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:14.796</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -331,27 +331,27 @@
</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>02:33.234</p></td>
+<td><p>02:38.971</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>01:21.556</p></td>
+<td><p>01:19.510</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>00:44.147</p></td>
+<td><p>00:42.913</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>00:17.066</p></td>
+<td><p>00:16.671</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>00:08.844</p></td>
+<tr class="row-odd"><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>00:08.453</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>00:08.832</p></td>
+<tr class="row-even"><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>00:08.279</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 4343c75d3..a34256135 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
@@ -486,39 +486,612 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
- allocate(conv2d_nchw: Pointer(local float32), float32, [2]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [336]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- for (rx.outer.outer: int32, 0, 3) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer: int32, 0, 2) {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + floordiv(threadIdx.x_1, 112)) < 3), dtype=bool) {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [336], [], scope="shared")[((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*224) + threadIdx.x_1)] = @tir.if_then_else(((((1 <= (floormod(blockIdx.x, 7) + floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + floordiv(threadIdx.x_1, 7)), 3))) && ((floormod(blockIdx.x, 7) + floormod(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer*2) + floordiv(threadIdx.x_1, 7)), 3)) < 8)) && (1 <= (r [...]
- }
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 31), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 31), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 6), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 6), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 62), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 62), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 37), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 43), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 43), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((threadIdx.x_1 < 54) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + ((floordiv(threadIdx.x_1, 9) + 2)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 74), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 74), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else((((threadIdx.x_1 < 23) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 49), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
}
- for (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1: int32, 0, 5) {
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 224;
- if @tir.likely((((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*7) + floordiv(threadIdx.x_2, 32)) < 32), dtype=bool) {
- for (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s: int32, 0, 3) {
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[(((ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*672) + (threadIdx.x_2*3)) + ax0.ax1.fused.ax2.fused.ax3.fused.inner.s)] = kernel[(((((((floordiv(blockIdx.x, 7)*294912) + (ax0.ax1.fused.ax2.fused.ax3.fused.outer.outer_1*64512)) + (floordiv(threadIdx.x_2, 16)*4608)) + (rc.outer.outer*144)) + (floormod(threadIdx.x_2, 16)*9)) + (ax0.ax1.fused.ax2.fused.ax3.fused.inner.s*3)) + rx.outer.outer)]
- }
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 56), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 112), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 168), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 224), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 280), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 336), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 448), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 560), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 616), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 672), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 728), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 8), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 64), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 840), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 24)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 896), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 32), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 952), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 16), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1064), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1120), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 40), 72), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
}
- for (rc.inner: int32, 0, 16) {
- for (ry.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.inner*21) + (ry.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.inner*3)) + ry.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.inner*21) + (ry.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.inner*3)) + ry.inner) + 1536)]))
- }
+ for (rc.outer.inner: int32, 0, 2) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 3)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 4)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 5)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 6)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 8)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 85)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 86)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 87)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 88)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 89)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 165)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 166)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 167)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 170)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 246)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 247)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 248)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 249)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 250)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 251)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 12)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 13)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 15)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 16)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 17)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 93)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 94)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 95)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 96)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 97)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 174)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 175)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 177)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 178)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 179)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 255)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 256)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 257)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 258)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 22)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 23)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 24)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 25)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 26)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 102)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 103)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 104)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 107)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 183)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 184)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 185)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 186)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 187)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 188)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 264)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 265)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 268)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + (floormod(threadIdx.x, 7)*9)) + 269)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
}
}
}
- compute[((((floordiv(blockIdx.x, 7)*3136) + (floordiv(threadIdx.x, 7)*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*64) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((((floordiv(blockIdx.x, 7)*3136) + (floordiv(threadIdx.x, 7)*49)) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x, 7)) + 1568)] = max((conv2d_nchw_1[1] + bias[(((floordiv(blockIdx.x, 7)*64) + floordiv(threadIdx.x, 7)) + 32)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (floormod(threadIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
+ }
}
}
</pre></div>
@@ -554,7 +1127,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<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: 0.409 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.215 ms
</pre></div>
</div>
</div>
@@ -584,35 +1157,35 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=32)
-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_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=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
-conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
+conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=7)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+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=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+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=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -630,16 +1203,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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=3)
+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=224)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=224)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 0)
+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:
@@ -657,38 +1230,576 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(224) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[2];
- __shared__ float pad_temp_shared[336];
- __shared__ float kernel_shared[3072];
+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[14];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer < 2; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) / 112)) < 3) {
- pad_temp_shared[((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 224) + ((int)threadIdx.x))] = (((((1 <= ((((int)blockIdx.x) % 7) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) / 7)) % 3))) && (((((int)blockIdx.x) % 7) + (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer * 2) + (((int)threadIdx.x) / 7)) % 3)) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) [...]
- }
- }
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 = 0; ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 < 5; ++ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1) {
- if (((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 * 7) + (((int)threadIdx.x) >> 5)) < 32) {
- for (int ax0_ax1_fused_ax2_fused_ax3_fused_inner_s = 0; ax0_ax1_fused_ax2_fused_ax3_fused_inner_s < 3; ++ax0_ax1_fused_ax2_fused_ax3_fused_inner_s) {
- kernel_shared[(((ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 * 672) + (((int)threadIdx.x) * 3)) + ax0_ax1_fused_ax2_fused_ax3_fused_inner_s)] = kernel[((((((((((int)blockIdx.x) / 7) * 294912) + (ax0_ax1_fused_ax2_fused_ax3_fused_outer_outer1 * 64512)) + ((((int)threadIdx.x) >> 4) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) & 15) * 9)) + (ax0_ax1_fused_ax2_fused_ax3_fused_inner_s * 3)) + rx_outer_outer)];
- }
- }
- }
- __syncthreads();
- for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
- for (int ry_inner = 0; ry_inner < 3; ++ry_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_inner * 21) + (ry_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_inner * 3)) + ry_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_inner * 21) + (ry_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_inner * 3)) + ry_inner) + 1536)]));
- }
- }
+ 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;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 81) * 49)) + (((((int)threadIdx.x) + 6) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + (((((int)threadIdx.x) + 12) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 504) / 81) * 49)) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) + 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 32) {
+ pad_temp_shared[(((int)threadIdx.x) + 616)] = ((((((int)threadIdx.x) < 23) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 616) / 81) * 49)) + (((((int)threadIdx.x) + 49) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 8) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 3) + 16) % 24) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 40) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ __syncthreads();
+ for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 3)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 4)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 5)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 6)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 8)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 85)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 86)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 87)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 88)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 89)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 165)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 166)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 167)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 170)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 246)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 247)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 248)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 249)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 250)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 251)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 12)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 13)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 15)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 16)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 17)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 93)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 94)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 95)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 96)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 97)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 174)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 175)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 177)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 178)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 179)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 255)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 256)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 257)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 258)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 22)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 23)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 24)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 25)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 26)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 102)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 103)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 104)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 107)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 183)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 184)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 185)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 186)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 187)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 188)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 264)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 265)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 268)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + ((((int)threadIdx.x) % 7) * 9)) + 269)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ }
+ }
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + ((((int)threadIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
- compute[(((((((int)blockIdx.x) / 7) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[((((((((int)blockIdx.x) / 7) * 3136) + ((((int)threadIdx.x) / 7) * 49)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) + 1568)] = max((conv2d_nchw[1] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) / 7)) + 32)]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -724,7 +1835,7 @@ 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> ( 2 minutes 33.234 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 38.971 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 86c8102a9..5da91e059 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -901,7 +901,7 @@ 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)
- 9.8089 9.8375 9.8414 9.7478 0.0432
+ 9.8854 9.8812 9.8988 9.8763 0.0096
</pre></div>
</div>
</div>
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 3d15aad5a..b614afe25 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -920,7 +920,7 @@ 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)
- 759.9897 759.5531 761.2447 759.1715 0.9009
+ 745.6005 745.6069 746.1523 745.0421 0.4533
</pre></div>
</div>
</div>
@@ -942,7 +942,7 @@ 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 21.556 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.510 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 13c1fba29..43c7ceb78 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -620,19 +620,23 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 32) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [512], [])[((i.outer.inner*16) + j.init)] = 0f32
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*256) + (i.inner.init*16)) + j.init)] = 0f32
+ }
}
for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (j: int32, 0, 16) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
- let cse_var_3: int32 = ((i.outer.inner*16) + j)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ if @tir.likely((elem_idx < (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])), dtype=bool) {
+ let cse_var_3: int32 = (((i.outer.inner*256) + (i.inner*16)) + j)
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
+ }
}
}
}
@@ -677,7 +681,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 2.289 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.661 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 825e82ad5..bbafd93ac 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:43.318</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:43.987</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,7 +331,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:43.289</p></td>
+<td><p>00:43.958</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>
@@ -342,11 +342,11 @@
<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_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-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>
<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_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-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>
<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 bd704f9aa..f9ac9dd47 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1164,8 +1164,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 42.40/42.40 result: MeasureResult(costs=(0.0054599264210526315,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6463680267333984, timestamp=1656533855.9871092) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 6 GFLOPS: 110.46/110.46 result: MeasureResult(costs=(0.0020958639791666665,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.828981876373291, timestamp=1656541832.4940493) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1288,7 +1288,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1411,7 +1411,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1534,7 +1534,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/110.46 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
@@ -1552,7 +1552,7 @@ No: 10 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('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', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1675,7 +1675,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1798,7 +1798,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1921,7 +1921,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2044,7 +2044,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2167,7 +2167,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2290,7 +2290,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2413,7 +2413,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2536,7 +2536,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, 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, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/42.40 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/110.46 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2624,7 +2624,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fcc6bfc2fa2
+ 12: 0x00007fb161115fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2689,7 +2689,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 143.88/143.88 result: MeasureResult(costs=(0.00160893531,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4241416454315186, timestamp=1656533882.6151175) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 142.44/142.44 result: MeasureResult(costs=(0.0016252628000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3169445991516113, timestamp=1656541858.9688838) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2730,7 +2730,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
-Time cost of this operator: 0.002009
+Time cost of this operator: 0.001990
</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 99cd46a85..67bf6cb46 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -578,10 +578,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.8 98.639 (1, 2, 10, 10, 3) 2 1 [311.8]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.121 0.987 (1, 6, 10, 10) 1 1 [3.121]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.18 0.373 (1, 1, 10, 10, 3) 1 1 [1.18]
-Total_time - 316.101 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 309.1 98.701 (1, 2, 10, 10, 3) 2 1 [309.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.106 0.992 (1, 6, 10, 10) 1 1 [3.106]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.963 0.308 (1, 1, 10, 10, 3) 1 1 [0.963]
+Total_time - 313.169 - - - - -
</pre></div>
</div>
</div>
@@ -634,10 +634,10 @@ Total_time -
########## 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 80.562 96.629 (1, 6, 10, 10, 1) 2 1 [80.562]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.844 2.211 (1, 6, 10, 10) 1 1 [1.844]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.967 1.16 (1, 1, 10, 10, 3) 1 1 [0.967]
-Total_time - 83.373 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 152.2 98.242 (1, 6, 10, 10, 1) 2 1 [152.2]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.768 1.141 (1, 6, 10, 10) 1 1 [1.768]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.956 0.617 (1, 1, 10, 10, 3) 1 1 [0.956]
+Total_time - 154.924 - - - - -
</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_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 75aaf213f..b261c4fab 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -510,7 +510,7 @@ 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/tmp9bak8r59/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp4zkvdb3h/images/random'
</pre></div>
</div>
</div>
@@ -570,8 +570,8 @@ 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], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [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/tmp9bak8r59/images/target contains 8144 images
-/tmp/tmp9bak8r59/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [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/tmp4zkvdb3h/images/target contains 8144 images
+/tmp/tmp4zkvdb3h/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -683,13 +683,13 @@ 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 - 56s - loss: 0.2288 - accuracy: 0.9210 - val_loss: 0.1531 - val_accuracy: 0.9581
+328/328 - 55s - loss: 0.2280 - accuracy: 0.9221 - val_loss: 0.1282 - val_accuracy: 0.9596
Epoch 2/3
-328/328 - 53s - loss: 0.0975 - accuracy: 0.9617 - val_loss: 0.1320 - val_accuracy: 0.9588
+328/328 - 52s - loss: 0.0972 - accuracy: 0.9661 - val_loss: 0.1109 - val_accuracy: 0.9671
Epoch 3/3
-328/328 - 53s - loss: 0.0652 - accuracy: 0.9758 - val_loss: 0.1244 - val_accuracy: 0.9668
+328/328 - 52s - loss: 0.0659 - accuracy: 0.9754 - val_loss: 0.1274 - val_accuracy: 0.9585
-<keras.callbacks.History object at 0x7f8d83287210>
+<keras.callbacks.History object at 0x7f363b3fdd10>
</pre></div>
</div>
</div>
@@ -951,7 +951,7 @@ 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> ( 9 minutes 44.227 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 8 minutes 37.672 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 b2ca582a7..6fc0a08be 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>10:32.973</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>09:23.343</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</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>09:44.227</p></td>
+<td><p>08:37.672</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:45.152</p></td>
+<td><p>00:42.225</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>00:03.595</p></td>
+<td><p>00:03.446</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 ccb309bc6..511617ede 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:11.613</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:11.279</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><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>00:10.027</p></td>
+<td><p>00:09.774</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>00:01.580</p></td>
+<td><p>00:01.499</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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 ec5665b6b..63b27c148 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -515,7 +515,7 @@ 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 0x7f8cf57339e0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f363a7a0320>
</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 40d3b6d27..6c41e16a1 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.133</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.050</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,31 +331,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.944</p></td>
+<td><p>00:01.903</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>00:00.938</p></td>
+<td><p>00:00.944</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>00:00.542</p></td>
+<td><p>00:00.521</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>00:00.531</p></td>
+<td><p>00:00.509</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.101</p></td>
+<td><p>00:00.098</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.038</p></td>
+<td><p>00:00.034</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.026</p></td>
+<td><p>00:00.027</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 47ead1338..31ad3ec37 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -571,7 +571,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpipwfxcf3/input0.cc'\nsource_filename = \"/tmp/tmpipwfxcf3/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 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpko97_vs6/input0.cc'\nsource_filename = \"/tmp/tmpko97_vs6/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 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 7e126558a..cd26fc812 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1597,7 +1597,7 @@ 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>
@@ -1881,7 +1881,7 @@ 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 e7606d70a..211c275c1 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/84c66da61/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 a40049631..7c6ae8f72 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/84c66da61/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 3b870b1fc..690409dc2 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/84c66da61/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 2b8c43a2d..f4a6328ba 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/84c66da61/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 908e89bc7..cb37eb726 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/84c66da61/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 62fbaa5f7..7c0e026fc 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/84c66da61/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 0103babe4..4b496b5ea 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/84c66da61/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 a7641bc4c..ac0afa262 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/84c66da61/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L1140">runtime.ts:1140</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/web/src/runtime.ts#L1140">runtime.ts:1140</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/84c66da61/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 b450c737c..094177a15 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/84c66da61/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 a2e1ff1a0..1a39bd650 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/84c66da61/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 fc669b2dd..74d55f417 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/84c66da61/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 02680ea4d..a07d53ad1 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/84c66da61/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 527716da1..7bc1a5e91 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/84c66da61/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 7981df904..08b33a3bf 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/84c66da61/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 a38e534d3..e1a8785ab 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/84c66da61/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/web/src/webgpu.ts#L170">webgpu.ts:170</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/84c66da61/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 4c4330bc9..fe3690d82 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/84c66da61/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 56e8c2195..e8716e1d9 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/84c66da61/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 797c1377f..30c64e883 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/84c66da61/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 dfd9d7857..927a74492 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/84c66da61/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 ef0a2c6dc..00e56d33f 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/84c66da61/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 641939b90..f9f4e1452 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/84c66da61/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L1362">runtime.ts:1362</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/web/src/runtime.ts#L1362">runtime.ts:1362</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/84c66da61/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 58f55aa57..81cbd4a52 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/84c66da61/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 e7f0d1b54..b5f6cd097 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/84c66da61/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 f3850966d..495954f8e 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/84c66da61/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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/84c66da61/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/b552bcf1d/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 066a6fa5c..076f554e6 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 3ad088543..57edfc31e 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:21.449</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.532</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -331,7 +331,7 @@
</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>00:21.442</p></td>
+<td><p>00:20.525</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 2f037e74d..cb0967268 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -566,7 +566,7 @@ 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 23.70s!
+resnet18_v1 inference graph built in 22.10s!
</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 99c5691a0..ec6324b1f 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -584,7 +584,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.29s!
+yolov3-tiny inference graph built in 15.60s!
</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 848f45562..8b211ba11 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>01:32.467</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:29.889</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<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>00:48.469</p></td>
+<td><p>00:47.748</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:43.998</p></td>
+<td><p>00:42.141</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 db031d6a3..415293158 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:03.239</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.179</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</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>00:02.839</p></td>
+<td><p>00:02.807</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.400</p></td>
+<td><p>00:00.372</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 4adc2608b..e64e8d2ea 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>00:00.744</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.681</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,11 +331,11 @@
</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>00:00.402</p></td>
+<td><p>00:00.366</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>00:00.342</p></td>
+<td><p>00:00.315</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 8fdb1fdfd..ab33255c0 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -561,7 +561,7 @@ operator fusion.</p>
<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: 94.244 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.724 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 363a9c301..f4bfac507 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -660,16 +660,16 @@ 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: 10.16/10.16 result: MeasureResult(costs=(0.026421065800000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5566368103027344, timestamp=1656532580.1935494) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.12/10.16 result: MeasureResult(costs=(0.1265065522,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1720869541168213, timestamp=1656532582.38161) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.70/11.70 result: MeasureResult(costs=(0.0229397172,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.554443359375, timestamp=1656532583.4443007) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.85/11.70 result: MeasureResult(costs=(0.145172307,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4352757930755615, timestamp=1656532586.4698496) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.65/11.70 result: MeasureResult(costs=(0.0734990044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3180365562438965, timestamp=1656532588.4477537) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.70/11.70 result: MeasureResult(costs=(0.1578454402,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.686985492706299, timestamp=1656532591.1802802) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/11.70 result: MeasureResult(costs=(0.309819843,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.0784971714019775, timestamp=1656532596.3024294) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.55/11.70 result: MeasureResult(costs=(0.0254460102,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.548879861831665, timestamp=1656532596.8743258) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.60/11.70 result: MeasureResult(costs=(0.16734202439999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7891955375671387, timestamp=1656532599.7862093) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.36/11.70 result: MeasureResult(costs=(0.11356567980000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9236400127410889, timestamp=1656532601.7674947) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.22/9.22 result: MeasureResult(costs=(0.0291259634,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5961494445800781, timestamp=1656540711.0033371) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.69/9.22 result: MeasureResult(costs=(0.0996186054,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7388560771942139, timestamp=1656540712.7610924) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.0228154048,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.555936336517334, timestamp=1656540713.8021886) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.73/11.77 result: MeasureResult(costs=(0.15525667840000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5837182998657227, timestamp=1656540716.4438019) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.63/11.77 result: MeasureResult(costs=(0.0740317612,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.320026159286499, timestamp=1656540717.8917458) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.83/11.77 result: MeasureResult(costs=(0.1463942162,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.460580587387085, timestamp=1656540720.907882) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.88/11.77 result: MeasureResult(costs=(0.3058933154,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.007894992828369, timestamp=1656540726.478014) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.69/11.77 result: MeasureResult(costs=(0.0251161864,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5427765846252441, timestamp=1656540727.0397494) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.92/11.77 result: MeasureResult(costs=(0.1399018654,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3358640670776367, timestamp=1656540729.4955604) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.79/11.77 result: MeasureResult(costs=(0.09623221959999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6406621932983398, timestamp=1656540731.1964812) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</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 7771f13af..8ccbaa0da 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -542,7 +542,7 @@ 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': 499.0021495500003, 'median': 499.1115282999999, 'std': 1.0006195570651975}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 492.78407607999964, 'median': 492.77864389999877, 'std': 0.3889919310436313}
</pre></div>
</div>
</div>
@@ -697,179 +697,179 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.34/ 17.34 GFLOPS | Progress: (4/20) | 6.40 s
-[Task 1/25] Current/Best: 6.16/ 17.34 GFLOPS | Progress: (8/20) | 9.41 s
-[Task 1/25] Current/Best: 11.48/ 22.63 GFLOPS | Progress: (12/20) | 11.87 s
-[Task 1/25] Current/Best: 16.76/ 22.69 GFLOPS | Progress: (16/20) | 13.56 s
-[Task 1/25] Current/Best: 11.60/ 23.86 GFLOPS | Progress: (20/20) | 15.32 s Done.
+[Task 1/25] Current/Best: 17.54/ 17.54 GFLOPS | Progress: (4/20) | 6.20 s
+[Task 1/25] Current/Best: 6.15/ 17.54 GFLOPS | Progress: (8/20) | 9.10 s
+[Task 1/25] Current/Best: 11.55/ 22.76 GFLOPS | Progress: (12/20) | 11.51 s
+[Task 1/25] Current/Best: 16.90/ 22.89 GFLOPS | Progress: (16/20) | 13.18 s
+[Task 1/25] Current/Best: 11.63/ 22.89 GFLOPS | Progress: (20/20) | 14.92 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.25/ 12.95 GFLOPS | Progress: (4/20) | 3.84 s
-[Task 2/25] Current/Best: 14.26/ 18.47 GFLOPS | Progress: (8/20) | 5.14 s
-[Task 2/25] Current/Best: 21.26/ 21.26 GFLOPS | Progress: (12/20) | 6.46 s
-[Task 2/25] Current/Best: 12.23/ 21.26 GFLOPS | Progress: (16/20) | 7.73 s
-[Task 2/25] Current/Best: 18.96/ 21.26 GFLOPS | Progress: (20/20) | 9.35 s Done.
+[Task 2/25] Current/Best: 12.25/ 12.86 GFLOPS | Progress: (4/20) | 3.78 s
+[Task 2/25] Current/Best: 14.19/ 18.13 GFLOPS | Progress: (8/20) | 5.10 s
+[Task 2/25] Current/Best: 21.08/ 21.08 GFLOPS | Progress: (12/20) | 6.41 s
+[Task 2/25] Current/Best: 12.92/ 21.08 GFLOPS | Progress: (16/20) | 7.66 s
+[Task 2/25] Current/Best: 19.80/ 21.08 GFLOPS | Progress: (20/20) | 9.25 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/ 10.55 GFLOPS | Progress: (4/20) | 5.91 s
-[Task 3/25] Current/Best: 15.50/ 16.88 GFLOPS | Progress: (8/20) | 7.83 s
-[Task 3/25] Current/Best: 14.88/ 16.88 GFLOPS | Progress: (12/20) | 9.55 s
-[Task 3/25] Current/Best: 7.20/ 23.69 GFLOPS | Progress: (16/20) | 11.49 s
-[Task 3/25] Current/Best: 12.49/ 23.69 GFLOPS | Progress: (20/20) | 16.05 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.50 GFLOPS | Progress: (4/20) | 5.85 s
+[Task 3/25] Current/Best: 15.60/ 16.89 GFLOPS | Progress: (8/20) | 7.76 s
+[Task 3/25] Current/Best: 14.91/ 16.89 GFLOPS | Progress: (12/20) | 9.48 s
+[Task 3/25] Current/Best: 7.23/ 23.86 GFLOPS | Progress: (16/20) | 11.37 s
+[Task 3/25] Current/Best: 12.60/ 23.86 GFLOPS | Progress: (20/20) | 15.88 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.55/ 20.22 GFLOPS | Progress: (4/20) | 2.41 s
-[Task 4/25] Current/Best: 6.65/ 20.22 GFLOPS | Progress: (8/20) | 6.85 s
-[Task 4/25] Current/Best: 21.60/ 21.60 GFLOPS | Progress: (12/20) | 11.54 s
-[Task 4/25] Current/Best: 16.99/ 21.60 GFLOPS | Progress: (16/20) | 13.79 s
-[Task 4/25] Current/Best: 13.13/ 21.60 GFLOPS | Progress: (20/20) | 15.72 s Done.
+[Task 4/25] Current/Best: 9.55/ 20.48 GFLOPS | Progress: (4/20) | 2.36 s
+[Task 4/25] Current/Best: 6.65/ 20.48 GFLOPS | Progress: (8/20) | 6.66 s
+[Task 4/25] Current/Best: 21.95/ 21.95 GFLOPS | Progress: (12/20) | 11.15 s
+[Task 4/25] Current/Best: 17.41/ 21.95 GFLOPS | Progress: (16/20) | 13.38 s
+[Task 4/25] Current/Best: 13.17/ 21.95 GFLOPS | Progress: (20/20) | 15.38 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.48/ 10.13 GFLOPS | Progress: (4/20) | 2.61 s
-[Task 5/25] Current/Best: 11.76/ 12.80 GFLOPS | Progress: (8/20) | 4.69 s
-[Task 5/25] Current/Best: 9.70/ 17.99 GFLOPS | Progress: (12/20) | 7.85 s
-[Task 5/25] Current/Best: 11.66/ 22.62 GFLOPS | Progress: (16/20) | 9.26 s
-[Task 5/25] Current/Best: 11.96/ 22.62 GFLOPS | Progress: (20/20) | 11.16 s Done.
+[Task 5/25] Current/Best: 9.94/ 10.40 GFLOPS | Progress: (4/20) | 2.57 s
+[Task 5/25] Current/Best: 11.92/ 12.80 GFLOPS | Progress: (8/20) | 4.61 s
+[Task 5/25] Current/Best: 11.38/ 18.13 GFLOPS | Progress: (12/20) | 7.66 s
+[Task 5/25] Current/Best: 11.83/ 22.41 GFLOPS | Progress: (16/20) | 9.06 s
+[Task 5/25] Current/Best: 12.01/ 22.41 GFLOPS | Progress: (20/20) | 10.87 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.26/ 20.74 GFLOPS | Progress: (4/20) | 4.00 s
-[Task 6/25] Current/Best: 18.94/ 20.74 GFLOPS | Progress: (8/20) | 5.77 s
-[Task 6/25] Current/Best: 13.20/ 20.74 GFLOPS | Progress: (12/20) | 7.70 s
-[Task 6/25] Current/Best: 19.89/ 20.74 GFLOPS | Progress: (16/20) | 9.93 s
-[Task 6/25] Current/Best: 3.72/ 20.74 GFLOPS | Progress: (20/20) | 12.48 s Done.
+[Task 6/25] Current/Best: 12.21/ 20.78 GFLOPS | Progress: (4/20) | 3.92 s
+[Task 6/25] Current/Best: 19.06/ 20.78 GFLOPS | Progress: (8/20) | 5.67 s
+[Task 6/25] Current/Best: 13.11/ 20.78 GFLOPS | Progress: (12/20) | 7.58 s
+[Task 6/25] Current/Best: 20.00/ 20.78 GFLOPS | Progress: (16/20) | 9.81 s
+[Task 6/25] Current/Best: 3.74/ 20.78 GFLOPS | Progress: (20/20) | 12.34 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.25/ 12.85 GFLOPS | Progress: (4/20) | 3.61 s
-[Task 7/25] Current/Best: 20.20/ 21.07 GFLOPS | Progress: (8/20) | 5.12 s
-[Task 7/25] Current/Best: 15.82/ 21.07 GFLOPS | Progress: (12/20) | 7.05 s
-[Task 7/25] Current/Best: 12.25/ 21.07 GFLOPS | Progress: (16/20) | 9.10 s
-[Task 7/25] Current/Best: 6.33/ 21.71 GFLOPS | Progress: (20/20) | 11.57 s Done.
+[Task 7/25] Current/Best: 11.20/ 12.82 GFLOPS | Progress: (4/20) | 3.59 s
+[Task 7/25] Current/Best: 20.33/ 21.09 GFLOPS | Progress: (8/20) | 5.08 s
+[Task 7/25] Current/Best: 16.17/ 21.09 GFLOPS | Progress: (12/20) | 6.97 s
+[Task 7/25] Current/Best: 12.27/ 21.09 GFLOPS | Progress: (16/20) | 8.99 s
+[Task 7/25] Current/Best: 6.41/ 21.86 GFLOPS | Progress: (20/20) | 11.43 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.18/ 14.08 GFLOPS | Progress: (4/20) | 2.91 s
-[Task 8/25] Current/Best: 9.36/ 14.08 GFLOPS | Progress: (8/20) | 7.72 s
-[Task 8/25] Current/Best: 12.92/ 14.08 GFLOPS | Progress: (12/20) | 13.95 s
-[Task 8/25] Current/Best: 18.92/ 18.92 GFLOPS | Progress: (16/20) | 16.06 s
-[Task 8/25] Current/Best: 19.86/ 19.86 GFLOPS | Progress: (20/20) | 22.57 s Done.
+[Task 8/25] Current/Best: 10.13/ 13.91 GFLOPS | Progress: (4/20) | 2.90 s
+[Task 8/25] Current/Best: 9.69/ 13.91 GFLOPS | Progress: (8/20) | 7.60 s
+[Task 8/25] Current/Best: 12.69/ 13.91 GFLOPS | Progress: (12/20) | 13.65 s
+[Task 8/25] Current/Best: 18.67/ 18.67 GFLOPS | Progress: (16/20) | 15.75 s
+[Task 8/25] Current/Best: 19.88/ 19.88 GFLOPS | Progress: (20/20) | 22.15 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.16/ 15.67 GFLOPS | Progress: (4/20) | 11.99 s
-[Task 9/25] Current/Best: 22.44/ 22.44 GFLOPS | Progress: (8/20) | 13.77 s
-[Task 9/25] Current/Best: 8.22/ 22.44 GFLOPS | Progress: (12/20) | 16.14 s
-[Task 9/25] Current/Best: 17.54/ 22.44 GFLOPS | Progress: (16/20) | 18.82 s
-[Task 9/25] Current/Best: 8.92/ 22.44 GFLOPS | Progress: (20/20) | 26.64 s
+[Task 9/25] Current/Best: 14.36/ 15.82 GFLOPS | Progress: (4/20) | 11.95 s
+[Task 9/25] Current/Best: 23.48/ 23.48 GFLOPS | Progress: (8/20) | 13.75 s
+[Task 9/25] Current/Best: 8.26/ 23.48 GFLOPS | Progress: (12/20) | 16.05 s
+[Task 9/25] Current/Best: 18.05/ 23.48 GFLOPS | Progress: (16/20) | 18.68 s
+[Task 9/25] Current/Best: 9.01/ 23.48 GFLOPS | Progress: (20/20) | 26.16 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/20) | 2.59 s
-[Task 10/25] Current/Best: 15.44/ 18.14 GFLOPS | Progress: (8/20) | 4.17 s
-[Task 10/25] Current/Best: 12.58/ 18.98 GFLOPS | Progress: (12/20) | 5.71 s
-[Task 10/25] Current/Best: 19.12/ 20.36 GFLOPS | Progress: (16/20) | 6.83 s
-[Task 10/25] Current/Best: 8.86/ 20.36 GFLOPS | Progress: (20/20) | 8.39 s Done.
+[Task 10/25] Current/Best: 18.12/ 18.12 GFLOPS | Progress: (4/20) | 2.55 s
+[Task 10/25] Current/Best: 15.55/ 18.12 GFLOPS | Progress: (8/20) | 4.18 s
+[Task 10/25] Current/Best: 12.79/ 19.03 GFLOPS | Progress: (12/20) | 5.69 s
+[Task 10/25] Current/Best: 19.07/ 20.36 GFLOPS | Progress: (16/20) | 6.80 s
+[Task 10/25] Current/Best: 8.79/ 20.36 GFLOPS | Progress: (20/20) | 8.34 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.32/ 18.01 GFLOPS | Progress: (4/20) | 3.32 s
-[Task 11/25] Current/Best: 16.03/ 18.01 GFLOPS | Progress: (8/20) | 6.05 s
-[Task 11/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (12/20) | 8.11 s
-[Task 11/25] Current/Best: 13.07/ 21.12 GFLOPS | Progress: (16/20) | 10.95 s
-[Task 11/25] Current/Best: 19.35/ 21.50 GFLOPS | Progress: (20/20) | 13.00 s Done.
+[Task 11/25] Current/Best: 12.26/ 18.15 GFLOPS | Progress: (4/20) | 3.31 s
+[Task 11/25] Current/Best: 16.93/ 18.15 GFLOPS | Progress: (8/20) | 6.04 s
+[Task 11/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (12/20) | 8.10 s
+[Task 11/25] Current/Best: 13.40/ 21.22 GFLOPS | Progress: (16/20) | 10.86 s
+[Task 11/25] Current/Best: 19.48/ 21.60 GFLOPS | Progress: (20/20) | 12.87 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.65/ 18.11 GFLOPS | Progress: (4/20) | 5.46 s
-[Task 12/25] Current/Best: 5.24/ 18.11 GFLOPS | Progress: (8/20) | 9.19 s
-[Task 12/25] Current/Best: 19.06/ 19.06 GFLOPS | Progress: (12/20) | 11.20 s
-[Task 12/25] Current/Best: 12.69/ 19.06 GFLOPS | Progress: (16/20) | 13.99 s
-[Task 12/25] Current/Best: 15.23/ 19.06 GFLOPS | Progress: (20/20) | 15.90 s Done.
+[Task 12/25] Current/Best: 7.82/ 18.15 GFLOPS | Progress: (4/20) | 5.24 s
+[Task 12/25] Current/Best: 5.30/ 18.15 GFLOPS | Progress: (8/20) | 8.87 s
+[Task 12/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (12/20) | 10.83 s
+[Task 12/25] Current/Best: 15.62/ 18.95 GFLOPS | Progress: (16/20) | 13.59 s
+[Task 12/25] Current/Best: 15.13/ 19.08 GFLOPS | Progress: (20/20) | 15.51 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.85/ 17.18 GFLOPS | Progress: (4/20) | 3.70 s
-[Task 13/25] Current/Best: 15.79/ 20.88 GFLOPS | Progress: (8/20) | 6.16 s
-[Task 13/25] Current/Best: 19.08/ 21.25 GFLOPS | Progress: (12/20) | 9.09 s
-[Task 13/25] Current/Best: 12.21/ 21.25 GFLOPS | Progress: (16/20) | 12.53 s
-[Task 13/25] Current/Best: 18.61/ 21.25 GFLOPS | Progress: (20/20) | 14.79 s Done.
+[Task 13/25] Current/Best: 8.59/ 17.35 GFLOPS | Progress: (4/20) | 3.68 s
+[Task 13/25] Current/Best: 16.15/ 21.04 GFLOPS | Progress: (8/20) | 6.07 s
+[Task 13/25] Current/Best: 19.54/ 21.04 GFLOPS | Progress: (12/20) | 8.98 s
+[Task 13/25] Current/Best: 12.24/ 21.04 GFLOPS | Progress: (16/20) | 12.40 s
+[Task 13/25] Current/Best: 18.79/ 21.04 GFLOPS | Progress: (20/20) | 14.62 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.57/ 13.57 GFLOPS | Progress: (4/20) | 3.36 s
-[Task 14/25] Current/Best: 6.09/ 13.57 GFLOPS | Progress: (8/20) | 5.55 s
-[Task 14/25] Current/Best: 21.15/ 21.15 GFLOPS | Progress: (12/20) | 8.09 s
-[Task 14/25] Current/Best: 16.79/ 21.15 GFLOPS | Progress: (16/20) | 9.75 s Done.
+[Task 14/25] Current/Best: 13.57/ 13.57 GFLOPS | Progress: (4/20) | 3.33 s
+[Task 14/25] Current/Best: 6.11/ 13.57 GFLOPS | Progress: (8/20) | 5.52 s
+[Task 14/25] Current/Best: 21.12/ 21.12 GFLOPS | Progress: (12/20) | 8.03 s
+[Task 14/25] Current/Best: 17.28/ 21.12 GFLOPS | Progress: (16/20) | 9.68 s Done.
-[Task 14/25] Current/Best: 17.17/ 21.15 GFLOPS | Progress: (20/20) | 11.50 s
+[Task 14/25] Current/Best: 17.07/ 21.12 GFLOPS | Progress: (20/20) | 11.40 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.00/ 17.60 GFLOPS | Progress: (4/20) | 2.76 s
-[Task 15/25] Current/Best: 14.42/ 17.96 GFLOPS | Progress: (8/20) | 4.10 s
-[Task 15/25] Current/Best: 10.35/ 22.18 GFLOPS | Progress: (12/20) | 6.20 s
-[Task 15/25] Current/Best: 20.36/ 22.18 GFLOPS | Progress: (16/20) | 9.20 s
-[Task 15/25] Current/Best: 9.68/ 22.18 GFLOPS | Progress: (20/20) | 10.18 s
+[Task 15/25] Current/Best: 16.17/ 17.68 GFLOPS | Progress: (4/20) | 2.71 s
+[Task 15/25] Current/Best: 14.52/ 18.06 GFLOPS | Progress: (8/20) | 4.05 s
+[Task 15/25] Current/Best: 10.38/ 22.33 GFLOPS | Progress: (12/20) | 6.11 s
+[Task 15/25] Current/Best: 20.37/ 22.33 GFLOPS | Progress: (16/20) | 8.97 s
+[Task 15/25] Current/Best: 9.72/ 22.33 GFLOPS | Progress: (20/20) | 9.94 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.86/ 20.86 GFLOPS | Progress: (4/20) | 2.98 s
-[Task 16/25] Current/Best: 3.00/ 20.86 GFLOPS | Progress: (8/20) | 4.62 s
-[Task 16/25] Current/Best: 19.49/ 20.86 GFLOPS | Progress: (12/20) | 5.85 s
-[Task 16/25] Current/Best: 17.43/ 20.86 GFLOPS | Progress: (16/20) | 7.23 s
-[Task 16/25] Current/Best: 10.01/ 22.09 GFLOPS | Progress: (20/20) | 9.27 s Done.
+[Task 16/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (4/20) | 2.95 s
+[Task 16/25] Current/Best: 3.04/ 20.66 GFLOPS | Progress: (8/20) | 4.56 s
+[Task 16/25] Current/Best: 19.49/ 20.66 GFLOPS | Progress: (12/20) | 5.78 s
+[Task 16/25] Current/Best: 17.72/ 20.66 GFLOPS | Progress: (16/20) | 7.11 s
+[Task 16/25] Current/Best: 10.05/ 21.97 GFLOPS | Progress: (20/20) | 9.14 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.93/ 18.79 GFLOPS | Progress: (4/20) | 4.74 s
-[Task 17/25] Current/Best: 14.20/ 22.88 GFLOPS | Progress: (8/20) | 7.63 s
-[Task 17/25] Current/Best: 16.74/ 22.88 GFLOPS | Progress: (12/20) | 9.71 s
-[Task 17/25] Current/Best: 16.49/ 22.88 GFLOPS | Progress: (16/20) | 11.88 s
-[Task 17/25] Current/Best: 10.02/ 22.88 GFLOPS | Progress: (20/20) | 14.02 s Done.
+[Task 17/25] Current/Best: 12.09/ 18.45 GFLOPS | Progress: (4/20) | 4.72 s
+[Task 17/25] Current/Best: 14.41/ 23.34 GFLOPS | Progress: (8/20) | 7.57 s
+[Task 17/25] Current/Best: 16.81/ 23.34 GFLOPS | Progress: (12/20) | 9.61 s
+[Task 17/25] Current/Best: 16.55/ 23.34 GFLOPS | Progress: (16/20) | 11.72 s
+[Task 17/25] Current/Best: 10.05/ 23.34 GFLOPS | Progress: (20/20) | 13.82 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.12/ 17.78 GFLOPS | Progress: (4/20) | 3.73 s
-[Task 18/25] Current/Best: 10.57/ 18.38 GFLOPS | Progress: (8/20) | 7.25 s
-[Task 18/25] Current/Best: 18.67/ 18.67 GFLOPS | Progress: (12/20) | 9.18 s
-[Task 18/25] Current/Best: 9.94/ 18.67 GFLOPS | Progress: (16/20) | 12.81 s
-[Task 18/25] Current/Best: 20.66/ 20.66 GFLOPS | Progress: (20/20) | 14.33 s Done.
+[Task 18/25] Current/Best: 11.03/ 17.81 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 18/25] Current/Best: 10.61/ 17.84 GFLOPS | Progress: (8/20) | 7.03 s
+[Task 18/25] Current/Best: 19.30/ 19.30 GFLOPS | Progress: (12/20) | 8.94 s
+[Task 18/25] Current/Best: 10.05/ 19.30 GFLOPS | Progress: (16/20) | 12.46 s
+[Task 18/25] Current/Best: 20.87/ 20.87 GFLOPS | Progress: (20/20) | 13.98 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 6.90/ 20.08 GFLOPS | Progress: (4/20) | 6.12 s
-[Task 19/25] Current/Best: 2.60/ 20.08 GFLOPS | Progress: (8/20) | 9.38 s
-[Task 19/25] Current/Best: 19.42/ 21.10 GFLOPS | Progress: (12/20) | 12.15 s
-[Task 19/25] Current/Best: 15.11/ 21.10 GFLOPS | Progress: (16/20) | 14.94 s
-[Task 19/25] Current/Best: 2.69/ 23.17 GFLOPS | Progress: (20/20) | 17.72 s Done.
+[Task 19/25] Current/Best: 6.93/ 20.34 GFLOPS | Progress: (4/20) | 6.01 s
+[Task 19/25] Current/Best: 2.60/ 20.34 GFLOPS | Progress: (8/20) | 9.26 s
+[Task 19/25] Current/Best: 20.24/ 21.57 GFLOPS | Progress: (12/20) | 12.03 s
+[Task 19/25] Current/Best: 15.50/ 21.57 GFLOPS | Progress: (16/20) | 14.82 s
+[Task 19/25] Current/Best: 2.70/ 23.70 GFLOPS | Progress: (20/20) | 17.61 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.78/ 14.84 GFLOPS | Progress: (4/20) | 3.36 s Done.
+[Task 20/25] Current/Best: 9.22/ 15.15 GFLOPS | Progress: (4/20) | 3.27 s Done.
Done.
-[Task 20/25] Current/Best: 10.27/ 14.84 GFLOPS | Progress: (8/20) | 6.82 s
-[Task 20/25] Current/Best: 2.32/ 16.51 GFLOPS | Progress: (12/20) | 10.78 s
-[Task 20/25] Current/Best: 12.50/ 16.51 GFLOPS | Progress: (16/20) | 14.41 s
-[Task 20/25] Current/Best: 13.36/ 21.60 GFLOPS | Progress: (20/20) | 16.49 s
+[Task 20/25] Current/Best: 9.43/ 15.15 GFLOPS | Progress: (8/20) | 6.54 s
+[Task 20/25] Current/Best: 2.32/ 16.15 GFLOPS | Progress: (12/20) | 10.44 s
+[Task 20/25] Current/Best: 12.41/ 16.15 GFLOPS | Progress: (16/20) | 14.08 s
+[Task 20/25] Current/Best: 13.22/ 22.22 GFLOPS | Progress: (20/20) | 16.15 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.38/ 17.72 GFLOPS | Progress: (4/20) | 3.26 s
-[Task 21/25] Current/Best: 14.39/ 17.72 GFLOPS | Progress: (8/20) | 4.83 s
-[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 6.99 s
-[Task 21/25] Current/Best: 18.04/ 18.04 GFLOPS | Progress: (16/20) | 10.45 s
-[Task 21/25] Current/Best: 4.47/ 18.04 GFLOPS | Progress: (20/20) | 17.64 s
+[Task 21/25] Current/Best: 6.40/ 17.60 GFLOPS | Progress: (4/20) | 3.19 s
+[Task 21/25] Current/Best: 14.66/ 17.60 GFLOPS | Progress: (8/20) | 4.75 s
+[Task 21/25] Current/Best: 1.61/ 17.60 GFLOPS | Progress: (12/20) | 6.90 s
+[Task 21/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (16/20) | 10.34 s
+[Task 21/25] Current/Best: 4.47/ 18.18 GFLOPS | Progress: (20/20) | 17.28 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 16.94 GFLOPS | Progress: (4/20) | 2.74 s
-[Task 22/25] Current/Best: 9.18/ 21.23 GFLOPS | Progress: (8/20) | 4.65 s
-[Task 22/25] Current/Best: 19.44/ 21.23 GFLOPS | Progress: (12/20) | 6.96 s
-[Task 22/25] Current/Best: 15.20/ 21.23 GFLOPS | Progress: (16/20) | 9.01 s
-[Task 22/25] Current/Best: 14.76/ 21.23 GFLOPS | Progress: (20/20) | 10.73 s Done.
+[Task 22/25] Current/Best: 2.70/ 17.05 GFLOPS | Progress: (4/20) | 2.65 s
+[Task 22/25] Current/Best: 8.62/ 22.01 GFLOPS | Progress: (8/20) | 4.62 s
+[Task 22/25] Current/Best: 19.89/ 22.01 GFLOPS | Progress: (12/20) | 6.93 s
+[Task 22/25] Current/Best: 15.45/ 22.01 GFLOPS | Progress: (16/20) | 9.00 s
+[Task 22/25] Current/Best: 14.34/ 22.01 GFLOPS | Progress: (20/20) | 10.70 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.42/ 20.24 GFLOPS | Progress: (4/20) | 3.26 s
-[Task 23/25] Current/Best: 15.45/ 20.24 GFLOPS | Progress: (8/20) | 6.63 s
-[Task 23/25] Current/Best: 20.69/ 21.26 GFLOPS | Progress: (12/20) | 8.46 s
-[Task 23/25] Current/Best: 5.92/ 21.26 GFLOPS | Progress: (16/20) | 15.72 s
-[Task 23/25] Current/Best: 7.48/ 21.26 GFLOPS | Progress: (20/20) | 19.99 s Done.
+[Task 23/25] Current/Best: 17.33/ 20.68 GFLOPS | Progress: (4/20) | 3.24 s
+[Task 23/25] Current/Best: 14.79/ 20.68 GFLOPS | Progress: (8/20) | 6.50 s
+[Task 23/25] Current/Best: 20.87/ 21.86 GFLOPS | Progress: (12/20) | 8.28 s
+[Task 23/25] Current/Best: 6.39/ 21.86 GFLOPS | Progress: (16/20) | 15.20 s
+[Task 23/25] Current/Best: 8.01/ 21.86 GFLOPS | Progress: (20/20) | 19.37 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.33/ 8.33 GFLOPS | Progress: (4/20) | 11.84 s
-[Task 24/25] Current/Best: 1.96/ 8.33 GFLOPS | Progress: (8/20) | 22.90 s
-[Task 24/25] Current/Best: 3.89/ 8.33 GFLOPS | Progress: (12/20) | 34.48 s Done.
+[Task 24/25] Current/Best: 8.26/ 8.26 GFLOPS | Progress: (4/20) | 11.78 s
+[Task 24/25] Current/Best: 3.76/ 8.26 GFLOPS | Progress: (8/20) | 23.01 s
+[Task 24/25] Current/Best: 4.68/ 8.26 GFLOPS | Progress: (12/20) | 33.72 s Done.
Done.
-[Task 24/25] Current/Best: 7.35/ 8.45 GFLOPS | Progress: (16/20) | 40.11 s
-[Task 24/25] Current/Best: 3.24/ 8.86 GFLOPS | Progress: (20/20) | 46.17 s Done.
+[Task 24/25] Current/Best: 6.28/ 9.30 GFLOPS | Progress: (16/20) | 39.11 s
+[Task 24/25] Current/Best: 3.44/ 9.30 GFLOPS | Progress: (20/20) | 44.89 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.54/ 2.89 GFLOPS | Progress: (4/20) | 11.61 s
-[Task 25/25] Current/Best: 5.50/ 7.52 GFLOPS | Progress: (8/20) | 22.90 s
-[Task 25/25] Current/Best: 5.84/ 7.52 GFLOPS | Progress: (12/20) | 34.33 s
-[Task 25/25] Current/Best: 5.72/ 8.59 GFLOPS | Progress: (16/20) | 36.08 s
-[Task 25/25] Current/Best: 2.92/ 8.72 GFLOPS | Progress: (20/20) | 46.77 s
+[Task 25/25] Current/Best: 1.55/ 2.76 GFLOPS | Progress: (4/20) | 11.54 s
+[Task 25/25] Current/Best: 6.09/ 8.20 GFLOPS | Progress: (8/20) | 22.82 s
+[Task 25/25] Current/Best: 6.01/ 8.20 GFLOPS | Progress: (12/20) | 34.27 s
+[Task 25/25] Current/Best: 5.87/ 8.92 GFLOPS | Progress: (16/20) | 36.10 s
+[Task 25/25] Current/Best: 2.88/ 8.92 GFLOPS | Progress: (20/20) | 46.79 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -972,8 +972,8 @@ 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': 414.98069430999976, 'median': 414.51188045000436, 'std': 1.4534486988092654}
-unoptimized: {'mean': 499.0021495500003, 'median': 499.1115282999999, 'std': 1.0006195570651975}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 411.4486063499976, 'median': 411.3848237999946, 'std': 0.7223690858981291}
+unoptimized: {'mean': 492.78407607999964, 'median': 492.77864389999877, 'std': 0.3889919310436313}
</pre></div>
</div>
</div>
@@ -987,7 +987,7 @@ 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> ( 10 minutes 18.790 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 8.755 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 4709bf998..44e9b5abe 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -518,7 +518,7 @@ 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>1.299e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.214e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index e9406227a..33e61a6c8 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -478,7 +478,7 @@ we can schedule the following series of operations ending with <code class="code
<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, 0x22804930)), stage(b, placeholder(b, 0x27bfddf0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[ [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x20829460)), stage(b, placeholder(b, 0x8bce2c0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[i [...]
</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 6ebcf1caa..9571bf64c 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -322,7 +322,7 @@
<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>13:03.333</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>12:50.374</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,35 +331,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:18.790</p></td>
+<td><p>10:08.755</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>01:02.459</p></td>
+<td><p>00:58.691</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>00:46.433</p></td>
+<td><p>00:49.520</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>00:28.661</p></td>
+<td><p>00:27.780</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>00:25.103</p></td>
+<td><p>00:23.644</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>00:01.030</p></td>
+<td><p>00:01.152</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>00:00.701</p></td>
+<td><p>00:00.682</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>00:00.155</p></td>
+<td><p>00:00.150</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 882d7b903..ff3d1727f 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -585,7 +585,7 @@ compile and run this new schedule with the parallel operation applied:</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallel: 0.000006
+parallel: 0.000007
</pre></div>
</div>
</div>
@@ -659,10 +659,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.161719999861817e-06 1.0
- naive 6.683999999999999e-06 0.8189450263073426
-parallel 6.0326e-06 0.739133417968533
- vector 2.4601700000000002e-05 3.0142788530379043
+ numpy 8.196840001346573e-06 1.0
+ naive 6.6586999999999995e-06 0.8123496370438013
+parallel 6.944500000000001e-06 0.8472167321625361
+ vector 2.4564900000000003e-05 2.996874404766287
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -978,7 +978,7 @@ 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: 0.019125
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018701
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1021,7 +1021,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.489482
+none: 3.240231
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1088,7 +1088,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.322924
+blocking: 0.303960
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1149,7 +1149,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.344663
+vectorization: 0.339425
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1206,7 +1206,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.127887
+loop permutation: 0.116881
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1284,7 +1284,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.110899
+array packing: 0.109708
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1360,7 +1360,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.113089
+block caching: 0.110648
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1429,7 +1429,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:268: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallelization: 0.146494
+parallelization: 0.144626
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1491,13 +1491,13 @@ 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 3.4894820561000004 1.0
- blocking 0.32292440769999997 0.09254221758655913
- vectorization 0.3446631945 0.09877202087842539
-loop permutation 0.127887387 0.03664938949218515
- array packing 0.1108994951 0.03178107619328072
- block caching 0.11308885370000002 0.03240849268799311
- parallelization 0.1464942655 0.04198166465533526
+ none 3.2402305365000004 1.0
+ blocking 0.303959731 0.09380805704285726
+ vectorization 0.33942504900000003 0.10475336405126184
+loop permutation 0.11688146609999998 0.03607195993722466
+ array packing 0.10970802340000001 0.03385809193641614
+ block caching 0.11064753860000001 0.034148045132467074
+ parallelization 0.14462649519999998 0.04463463126183027
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1529,7 +1529,6 @@ 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 2.459 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>