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 2022/06/18 10:50:58 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@f8b320f523b24fd8ddb8cf7026e61bbb4f4ea348)
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 ccae97f2c deploying docs (apache/tvm@f8b320f523b24fd8ddb8cf7026e61bbb4f4ea348)
ccae97f2c is described below
commit ccae97f2cede9cb2629f0e6d69007de705022a40
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sat Jun 18 10:50:51 2022 +0000
deploying docs (apache/tvm@f8b320f523b24fd8ddb8cf7026e61bbb4f4ea348)
---
docs/_sources/contribute/pull_request.rst.txt | 9 +
.../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 +-
.../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 | 4 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1283 +++++++++++++++++---
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 88 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../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 | 12 +-
.../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 | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 45 +-
docs/commit_hash | 2 +-
docs/contribute/pull_request.html | 7 +
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/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 19 +-
docs/how_to/deploy_models/deploy_prequantized.html | 7 +-
.../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 | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 16 +-
.../extend_tvm/bring_your_own_datatypes.html | 4 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1283 +++++++++++++++++---
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 88 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../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 | 12 +-
.../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 | 22 +-
docs/tutorial/tensor_expr_get_started.html | 41 +-
121 files changed, 3260 insertions(+), 1148 deletions(-)
diff --git a/docs/_sources/contribute/pull_request.rst.txt b/docs/_sources/contribute/pull_request.rst.txt
index 82b5c5d43..81852a212 100644
--- a/docs/_sources/contribute/pull_request.rst.txt
+++ b/docs/_sources/contribute/pull_request.rst.txt
@@ -113,6 +113,15 @@ each time (e.g. you can test a change in CPU and i386 while retaining incrementa
# run the CPU build and drop into a shell in the container
python tests/scripts/ci.py cpu --interactive
+We regularly update our docker images and, over time, stale images may unnecessarily consume disk
+space. You can remove stale images that aren't used in the presently checked-out branch plus any
+other worktrees using the following command:
+
+.. code:: bash
+
+ docker/clear-stale-images.sh
+
+Consult the ``--help`` for more options.
C++ (local)
^^^^^^^^^^^
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 67ac0304f..53b03d0fd 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.zip1f2109f5-9cd0-45c3-bfe6-371a0c53d0b9 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip185cf734-9ebd-4a95-aac6-c0c3dda4d326 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 0bb393115..a5adfe8a4 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<07:42, 94.0kB/s]
0%| | 48.0k/41.5M [00:00<04:52, 149kB/s]
0%| | 96.0k/41.5M [00:00<03:27, 209kB/s]
0%| | 192k/41.5M [00:00<02:04, 348kB/s]
1%| | 400k/41.5M [00:00<01:05, 661kB/s]
2%|1 | 808k/41.5M [00:01<00:34, 1.25MB/s]
4%|3 | 1.59M/41.5M [00:01<00:17, 2.40MB/s]
7%|7 | 3.07M/41.5M [00:01<00:09, 4.46MB/s]
11%|# | 4.55M/41.5M [00:01<00:06, 5.84MB/s]
15%|#4 | 6.03M/41.5M [00:01<00:05, 6.76MB/s]
18%|#8 | 7.52M/41.5M [00:01<00:04, 7.41MB/s]
22%|##1 | 8.99M/41.5M [00:02<00:04, 7.84MB/s]
25%|##5 | 10.5M/41.5M [00:02<00:03, 8.14MB/s]
29%|##8 | 11.9M/41.5M [00:02<00:03, 8.33MB/s]
32%|###2 | 13.4M/41.5M [00:02<00:03, 8.50MB/s]
36%|###5 | 14.9M/41.5M [00:02<00:03, 8.61MB/s]
39%|###9 | 16.4M/41.5M [00:02<0
0:03, 8.68MB/s]
43%|####3 | 17.9M/41.5M [00:03<00:02, 8.74MB/s]
47%|####6 | 19.4M/41.5M [00:03<00:02, 8.78MB/s]
50%|##### | 20.8M/41.5M [00:03<00:02, 8.79MB/s]
54%|#####3 | 22.3M/41.5M [00:03<00:02, 8.82MB/s]
57%|#####7 | 23.8M/41.5M [00:03<00:02, 8.84MB/s]
61%|###### | 25.3M/41.5M [00:04<00:01, 8.84MB/s]
64%|######4 | 26.8M/41.5M [00:04<00:01, 8.83MB/s]
68%|######8 | 28.2M/41.5M [00:04<00:01, 8.83MB/s]
72%|#######1 | 29.7M/41.5M [00:04<00:01, 8.85MB/s]
75%|#######5 | 31.2M/41.5M [00:04<00:01, 8.83MB/s]
79%|#######8 | 32.6M/41.5M [00:04<00:01, 8.80MB/s]
82%|########2 | 34.1M/41.5M [00:05<00:00, 8.80MB/s]
86%|########5 | 35.6M/41.5M [00:05<00:00, 8.82MB/s]
89%|########9 | 37.1M/41.5M [00:05<00:00, 8.81MB/s]
93%|#########2| 38.5M/41.5M [00:05<00:00, 8.82MB/s]
96%|#########6| 40.0M/41.5M [00:05<00:00, 8.83MB/s]
100%|##########| 41.5M/41.5M [00:05<00:00, 7.50MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:46, 93.3kB/s]
0%| | 48.0k/41.5M [00:00<04:54, 148kB/s]
0%| | 96.0k/41.5M [00:00<03:29, 207kB/s]
0%| | 160k/41.5M [00:00<02:39, 272kB/s]
1%| | 280k/41.5M [00:00<01:41, 424kB/s]
1%|1 | 520k/41.5M [00:01<00:57, 753kB/s]
2%|2 | 944k/41.5M [00:01<00:32, 1.31MB/s]
4%|4 | 1.82M/41.5M [00:01<00:16, 2.59MB/s]
8%|7 | 3.30M/41.5M [00:01<00:07, 5.08MB/s]
10%|# | 4.34M/41.5M [00:01<00:06, 5.73MB/s]
14%|#4 | 5.82M/41.5M [00:01<00:05, 6.75MB/s]
18%|#7 | 7.28M/41.5M [00:02<00:04, 7.37MB/s]
21%|##1 | 8.76M/41.5M [00:02<00:03, 8.95MB/s]
23%|##3 | 9.69M/41.5M [00:02<00:04, 7.98MB/s]
26%|##5 | 10.7M/41.5M [00:02<00:03, 8.30MB/s]
28%|##8 | 11.7M/41.5M [00:02<00:03, 7.99MB/s]
32%|###1 | 13.2M/41.5M [00:02<00:
03, 9.56MB/s]
34%|###4 | 14.2M/41.5M [00:02<00:03, 8.40MB/s]
36%|###6 | 15.1M/41.5M [00:02<00:03, 8.44MB/s]
39%|###8 | 16.1M/41.5M [00:03<00:03, 8.18MB/s]
42%|####2 | 17.6M/41.5M [00:03<00:02, 9.84MB/s]
45%|####4 | 18.6M/41.5M [00:03<00:02, 8.50MB/s]
47%|####7 | 19.6M/41.5M [00:03<00:02, 8.49MB/s]
50%|####9 | 20.6M/41.5M [00:03<00:02, 8.21MB/s]
53%|#####3 | 22.0M/41.5M [00:03<00:02, 9.80MB/s]
55%|#####5 | 23.0M/41.5M [00:03<00:02, 8.47MB/s]
58%|#####7 | 24.0M/41.5M [00:04<00:02, 8.54MB/s]
60%|###### | 25.0M/41.5M [00:04<00:02, 8.27MB/s]
64%|######3 | 26.4M/41.5M [00:04<00:01, 9.77MB/s]
66%|######6 | 27.4M/41.5M [00:04<00:01, 8.43MB/s]
68%|######8 | 28.4M/41.5M [00:04<00:01, 8.74MB/s]
71%|####### | 29.4M/41.5M [00:04<00:01, 9.18MB/s]
73%|#######3 | 30.4M/41.5M [00:04<00:01, 8.43MB/s]
76%|#######5 | 31.4M/41.5M [00:04<00:01, 8.75MB/s]
78%|#####
##8 | 32.4M/41.5M [00:04<00:01, 9.18MB/s]
80%|######## | 33.3M/41.5M [00:05<00:01, 8.38MB/s]
83%|########2 | 34.3M/41.5M [00:05<00:00, 8.75MB/s]
85%|########5 | 35.4M/41.5M [00:05<00:00, 8.60MB/s]
87%|########7 | 36.2M/41.5M [00:05<00:00, 8.39MB/s]
90%|########9 | 37.3M/41.5M [00:05<00:00, 8.77MB/s]
92%|#########2| 38.3M/41.5M [00:05<00:00, 8.78MB/s]
94%|#########4| 39.2M/41.5M [00:05<00:00, 8.53MB/s]
97%|#########6| 40.2M/41.5M [00:05<00:00, 9.01MB/s]
99%|#########9| 41.3M/41.5M [00:06<00:00, 9.42MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 7.13MB/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 91869824b..14201a528 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 6.200 seconds)
+ **Total running time of the script:** ( 1 minutes 7.750 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 7a649449e..0ef4a618b 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]
20%|## | 8.96M/44.7M [00:00<00:00, 87.7MB/s]
61%|###### | 27.2M/44.7M [00:00<00:00, 147MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 154MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
37%|###7 | 16.6M/44.7M [00:00<00:00, 174MB/s]
91%|######### | 40.4M/44.7M [00:00<00:00, 219MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 215MB/s]
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 f5056ebbf..ddd0fbcdd 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
=================
-**05:17.787** total execution time for **how_to_compile_models** files:
+**05:20.514** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:06.200 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:07.750 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 00:59.486 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 00:59.629 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:56.749 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:56.952 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.079 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.303 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:23.890 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.364 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:22.456 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:23.221 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.056 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.849 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.013 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.006 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.529 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.068 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.329 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.372 | 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 c27415a44..8a81d0463 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)
- 15.8340 15.8128 15.9222 15.7389 0.0611
+ 15.8829 15.8845 16.2002 15.6726 0.1733
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 468e153ba..3786afe4f 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]
9%|9 | 15.4M/170M [00:00<00:01, 161MB/s]
21%|##1 | 36.1M/170M [00:00<00:00, 194MB/s]
33%|###2 | 55.8M/170M [00:00<00:00, 200MB/s]
45%|####5 | 77.1M/170M [00:00<00:00, 209MB/s]
59%|#####8 | 99.5M/170M [00:00<00:00, 218MB/s]
72%|#######1 | 122M/170M [00:00<00:00, 224MB/s]
85%|########4 | 144M/170M [00:00<00:00, 226MB/s]
98%|#########7| 166M/170M [00:00<00:00, 228MB/s]
100%|##########| 170M/170M [00:00<00:00, 218MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
7%|7 | 12.1M/170M [00:00<00:01, 127MB/s]
20%|## | 34.2M/170M [00:00<00:00, 188MB/s]
36%|###5 | 60.6M/170M [00:00<00:00, 229MB/s]
51%|#####1 | 87.0M/170M [00:00<00:00, 248MB/s]
67%|######6 | 113M/170M [00:00<00:00, 258MB/s]
82%|########2 | 140M/170M [00:00<00:00, 265MB/s]
98%|#########7| 166M/170M [00:00<00:00, 269MB/s]
100%|##########| 170M/170M [00:00<00:00, 250MB/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:** ( 2 minutes 53.890 seconds)
+ **Total running time of the script:** ( 2 minutes 50.776 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 a8fb39c36..51561988b 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, 160MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
63%|######3 | 8.58M/13.6M [00:00<00:00, 89.9MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 108MB/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)
- 90.3393 90.2856 91.6459 90.1674 0.2036
+ 90.4142 90.2771 94.9720 90.0825 0.6962
@@ -448,7 +448,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.060 seconds)
+ **Total running time of the script:** ( 1 minutes 6.075 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 a95cc41c0..70c392014 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)
- 119.6619 119.6320 122.2336 118.9508 0.4077
+ 119.8766 119.8199 123.5409 118.8294 0.5558
@@ -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 56.349 seconds)
+ **Total running time of the script:** ( 1 minutes 54.807 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 6174fce94..17722632d 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:** ( 1 minutes 16.021 seconds)
+ **Total running time of the script:** ( 1 minutes 10.893 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 e8c00a98d..07f07aaa2 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]
4%|4 | 5504/132723 [00:00<00:02, 55037.17KB/s]
10%|# | 13792/132723 [00:00<00:01, 71409.99KB/s]
17%|#6 | 22461/132723 [00:00<00:01, 78381.56KB/s]
23%|##3 | 31060/132723 [00:00<00:01, 81381.89KB/s]
30%|##9 | 39655/132723 [00:00<00:01, 83027.31KB/s]
36%|###6 | 48258/132723 [00:00<00:01, 84046.35KB/s]
43%|####2 | 56788/132723 [00:00<00:00, 84454.30KB/s]
49%|####9 | 65340/132723 [00:00<00:00, 84790.48KB/s]
56%|#####5 | 73913/132723 [00:00<00:00, 85083.06KB/s]
62%|######2 | 82515/132723 [00:01<00:00, 85369.49KB/s]
69%|######8 | 91091/132723 [00:01<00:00, 85487.03KB/s]
75%|#######5 | 99678/132723 [00:01<00:00, 85600.57KB/s]
82%|########1 | 108243/132723 [00:01<00:00, 85612.97KB/s]
88%|########8 | 116805/132723 [00:01<00:00, 85573.96KB/s]
95%|#########4| 125468/132723 [00:01<00:00, 85890.15KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 83685.26KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6858/132723 [00:00<00:01, 68571.24KB/s]
11%|#1 | 15209/132723 [00:00<00:01, 77350.19KB/s]
17%|#7 | 22945/132723 [00:00<00:01, 71088.15KB/s]
24%|##3 | 31315/132723 [00:00<00:01, 75813.00KB/s]
29%|##9 | 38955/132723 [00:00<00:01, 72345.12KB/s]
36%|###5 | 47356/132723 [00:00<00:01, 76094.36KB/s]
42%|####1 | 55716/132723 [00:00<00:00, 78455.73KB/s]
48%|####8 | 64105/132723 [00:00<00:00, 80137.45KB/s]
55%|#####4 | 72613/132723 [00:00<00:00, 81653.70KB/s]
61%|######1 | 81031/132723 [00:01<00:00, 82422.56KB/s]
67%|######7 | 89294/132723 [00:01<00:00, 81116.66KB/s]
74%|#######3 | 97666/132723 [00:01<00:00, 81893.67KB/s]
80%|#######9 | 105870/132723 [00:01<00:00, 71576.00KB/s]
86%|########6 | 114331/132723 [00:01<00:00, 75117.84KB/s]
92%|#########2| 122722/132723 [00:01<00:00, 77575.93KB/s]
99%|########
#8| 131194/132723 [00:01<00:00, 79614.29KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77712.82KB/s]
@@ -240,7 +240,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 18.289 seconds)
+ **Total running time of the script:** ( 2 minutes 16.315 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 93633dff3..d7fe2b1a4 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
=================
-**10:21.098** total execution time for **how_to_deploy_models** files:
+**10:08.461** 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``) | 02:53.890 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:50.776 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:18.289 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:16.315 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:56.349 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:54.807 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:16.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:10.893 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.060 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.075 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.844 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:27.963 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.639 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.627 | 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 62592edca..fda5d89d3 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.zip956411ac-acf7-4678-bff3-fb659e097f32 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip9cea7fb9-22ce-40b1-aebb-8d0c6c1c78b3 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -577,7 +577,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
/workspace/python/tvm/driver/build_module.py:264: 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. "
- Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+ Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
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 045c06eef..021f1620d 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
=================
-**00:39.364** total execution time for **how_to_extend_tvm** files:
+**00:38.567** 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``) | 00:36.217 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:35.527 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.227 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.137 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.913 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.894 | 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 |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index e9c84cdf3..6224179c1 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: 6975us [6975us] (45.29%; 45.29%)
- FoldScaleAxis: 8426us [7us] (54.71%; 54.71%)
- FoldConstant: 8419us [1732us] (54.66%; 99.91%)
- InferType: 6686us [6686us] (43.42%; 79.42%)
+ InferType: 6527us [6527us] (45.71%; 45.71%)
+ FoldScaleAxis: 7752us [5us] (54.29%; 54.29%)
+ FoldConstant: 7747us [1569us] (54.25%; 99.93%)
+ InferType: 6178us [6178us] (43.26%; 79.75%)
@@ -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: 6576us [6576us] (44.80%; 44.80%)
- FoldScaleAxis: 8101us [5us] (55.20%; 55.20%)
- FoldConstant: 8096us [1660us] (55.16%; 99.94%)
- InferType: 6436us [6436us] (43.85%; 79.50%)
+ InferType: 6217us [6217us] (44.46%; 44.46%)
+ FoldScaleAxis: 7766us [5us] (55.54%; 55.54%)
+ FoldConstant: 7761us [1598us] (55.50%; 99.94%)
+ InferType: 6163us [6163us] (44.07%; 79.41%)
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 aec9557cf..a51cf5281 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: 44.969186 ms
+ Convolution: 34.788746 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 30d58ecb4..40a4d98c4 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: 6.915422 ms
+ conv2d with tensor core: 9.080938 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 ed7c2475c..73d369807 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: 0.018415
- Baseline: 3.340516
+ Numpy running time: 0.018322
+ Baseline: 3.286196
@@ -226,7 +226,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.297967
+ Opt1: 0.303289
@@ -329,7 +329,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.334222
+ Opt2: 0.327262
@@ -425,7 +425,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118283
+ Opt3: 0.117826
@@ -550,7 +550,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111485
+ Opt4: 0.110779
@@ -672,7 +672,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.112130
+ Opt5: 0.111495
@@ -797,7 +797,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145464
+ Opt6: 0.145484
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 a44ce8d62..18d5940d2 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:34.155** total execution time for **how_to_optimize_operators** files:
+**00:34.065** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.936 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:31.739 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.230 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.299 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.990 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.027 | 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 c1a3280d4..e89fee9f8 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
=================
-**05:10.819** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:23.995** 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``) | 02:33.823 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:37.630 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:19.605 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:19.543 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:43.015 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:42.335 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:17.334 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:27.898 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.557 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.358 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.485 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.232 | 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 263f920c0..a99053dca 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
@@ -239,84 +239,599 @@ 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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [252]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [96]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[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, [2016]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), 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
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 128) {
+ 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, 16) {
for (rx.outer.outer: int32, 0, 3) {
- let cse_var_1: int32 = (rc.outer.outer*196)
+ let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_1: int32 = (rc.outer.outer*1568)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [252], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_1 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv(threadIdx.x_1, 7) + 14), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dty [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv(threadIdx.x_1, 7) + 28), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((7 <= floormod((threadIdx.x_1*4), 63)) && (floormod((threadIdx.x_1*4), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1*4), 63)*49)) + rx.outer.outer) + floormod((threadIdx.x_1*4), 63)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*4) + 1), 63)) && (floormod(((threadIdx.x_1*4) + 1), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*4) + 1), 63)*49)) + rx.outer.outer) + floormod(((threadIdx.x_1*4) + 1), 63)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*4) + 2), 63)) && (floormod(((threadIdx.x_1*4) + 2), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*4) + 2), 63)*49)) + rx.outer.outer) + floormod(((threadIdx.x_1*4) + 2), 63)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*4) + 3), 63)) && (floormod(((threadIdx.x_1*4) + 3), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*4) + 3), 63)*49)) + rx.outer.outer) + floormod(((threadIdx.x_1*4) + 3), 63)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [96], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 12)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 12)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 32), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 5), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv((thr [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 32), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), data [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 32), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), data [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 32), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), data [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 64), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 1), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv((thr [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 64), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), data [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 64), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), data [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 64), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), data [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 96), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv((thr [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 96), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), data [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 96), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), data [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 96), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), data [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 128), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 2), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv((th [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 128), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 128), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 128), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), dat [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 160), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 7), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 7), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv((th [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 160), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 7), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 7), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 160), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 7), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 7), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 160), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 7), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 7), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), dat [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 192), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv((th [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 192), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 192), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 192), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), dat [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 224), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 8), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 8), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv((th [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 224), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 8), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 8), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 224), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 8), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 8), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 224), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 8), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 8), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), dat [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 256), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 4), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 4), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv((th [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 256), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 4), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 4), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 256), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 4), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 4), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), dat [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 256), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 4), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 4), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), dat [...]
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + cse_var_2) + (threadIdx.x_2*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 7), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 21), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 224), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 35), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 280), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 42), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 49), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 392), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 63), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 560), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 77), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 616), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 91), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 728), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 784), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 105), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 896), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 119), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 952), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 126), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 133), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1064), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1120), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 147), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 154), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1232), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 161), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1288), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 175), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1400), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 182), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1456), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 189), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((ry.outer.inner*7) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1029)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1036)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1043)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1050)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1092)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1099)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1113)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1232)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1239)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1295)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1302)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1358)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1365)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1421)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1428)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1484)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1533)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1547)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1554)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1596)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1610)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1617)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1659)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1673)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1680)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1722)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1736)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1743)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1785)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1799)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1806)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1848)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1862)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1869)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1911)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1925)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1932)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1974)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1988)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1995)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((ry.outer.inner*7) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1029)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1036)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1043)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1050)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1092)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1099)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1113)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1232)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1239)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1295)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1302)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1358)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1365)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1421)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1428)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1484)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1533)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1547)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1554)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1596)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1610)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1617)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1659)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1673)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1680)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1722)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1736)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1743)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1785)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1799)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1806)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1848)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1862)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1869)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1911)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1925)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1932)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1974)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1988)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1995)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 38)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 39)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 40)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 42)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 43)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 44)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*8) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i2.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -371,7 +886,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.332 ms
+ Execution time of this operator: 0.400 ms
@@ -420,32 +935,32 @@ 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=4)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_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_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=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=32)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_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)
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=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_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=7)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -468,14 +983,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+ 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)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+ 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", 64)
+ 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:
@@ -493,78 +1008,550 @@ 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__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[252];
- __shared__ float kernel_shared[96];
+ 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[2016];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ 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 < 16; ++rc_outer_outer) {
for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 56) {
- pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((int)threadIdx.x) < 49) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 12) * 3)) + rx_outer_outer)];
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((7 <= ((((int)threadIdx.x) * 4) % 63)) && (((((int)threadIdx.x) * 4) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 63) * 49)) + rx_outer_outer) + ((((int)threadIdx.x) * 4) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((7 <= (((((int)threadIdx.x) * 4) + 1) % 63)) && ((((((int)threadIdx.x) * 4) + 1) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 63) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 4) + 1) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((7 <= (((((int)threadIdx.x) * 4) + 2) % 63)) && ((((((int)threadIdx.x) * 4) + 2) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 63) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 4) + 2) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((7 <= (((((int)threadIdx.x) * 4) + 3) % 63)) && ((((((int)threadIdx.x) * 4) + 3) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 3) / 63) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 4) + 3) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 224) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 5) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 224) / 63) * 49)) + (((((((int)t [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 225) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 226) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 227) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 448) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 1) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 448) / 63) * 49)) + (((((((int)t [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 449) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 450) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 451) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 672) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 672) / 63) * 49)) + (((((((int)t [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 673) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 674) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 675) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 896) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 2) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 896) / 63) * 49)) + (((((((int)t [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 897) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 898) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 899) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1120) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 7) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1120) / 63) * 49)) + (((((((int [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1121) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 7) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 7) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1122) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 7) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 7) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1123) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 7) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 7) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1344) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1344) / 63) * 49)) + (((((((int [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1345) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1346) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1347) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1568) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 8) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 8) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1568) / 63) * 49)) + (((((((int [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1569) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 8) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 8) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1570) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 8) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 8) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1571) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 8) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 8) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1792) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 4) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 4) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1792) / 63) * 49)) + (((((((int [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1793) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 4) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1794) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 4) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1795) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 4) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * [...]
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 8) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 40) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 8) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 40) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 24) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 38)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 40)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 43)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 44)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 47)]));
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((ry_outer_inner * 7) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1029)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1036)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1043)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1050)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1092)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1099)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1113)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1232)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1239)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1295)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1302)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1358)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1365)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1421)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1428)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1484)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1533)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1547)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1554)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1596)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1610)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1617)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1659)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1673)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1680)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1722)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1736)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1743)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1785)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1799)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1806)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1848)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1862)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1869)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1911)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1925)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1932)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1974)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1988)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1995)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((ry_outer_inner * 7) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1029)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1036)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1043)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1050)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1092)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1099)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1113)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1232)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1239)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1295)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1302)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1358)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1365)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1421)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1428)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1484)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1533)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1547)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1554)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1596)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1610)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1617)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1659)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1673)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1680)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1722)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1736)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1743)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1785)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1799)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1806)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1848)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1862)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1869)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1911)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1925)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1932)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1974)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1988)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1995)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ }
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -626,7 +1613,7 @@ 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 33.823 seconds)
+ **Total running time of the script:** ( 2 minutes 37.630 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 602c63bbf..cf9e3a2fc 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)
- 10.1713 10.1826 10.1906 10.1407 0.0219
+ 9.5812 9.5758 9.6298 9.5379 0.0377
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 5f59ee124..07f7bb509 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)
- 759.3360 761.0120 761.4977 755.4984 2.7209
+ 762.0268 762.2833 763.4970 760.3000 1.3177
@@ -693,7 +693,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.605 seconds)
+ **Total running time of the script:** ( 1 minutes 19.543 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 09b10ceed..58b47b3dd 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
@@ -396,29 +396,81 @@ 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_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 32) {
- for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ for (i0.outer: int32, 0, 4) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 4) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- for (i.inner: int32, 0, 4) {
- for (j: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i0.outer*8192) + (i.outer.inner*2048)) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_2: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
- compute[ramp(cse_var_2, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = ((((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ }
}
}
}
@@ -474,7 +526,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.455 ms
+ Execution time of this operator: 1.819 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 e4be962a2..d6f899269 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
=================
-**00:42.689** total execution time for **how_to_tune_with_autotvm** files:
+**00:42.951** 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``) | 00:42.660 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:42.922 | 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``) | 00:00.005 | 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 |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 d73a9c2d7..e5015a720 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: 92.75/92.75 result: MeasureResult(costs=(0.002496006854166667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6259727478027344, timestamp=1655499340.9969175) [('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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 104.14/104.14 result: MeasureResult(costs=(0.0022229111875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6228270530700684, timestamp=1655547517.125957) [('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: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/104.14 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: 0.00/92.75 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/104.14 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: 0x00007f978e86bfa2
+ 12: 0x00007fabe7284fa2
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: 141.96/141.96 result: MeasureResult(costs=(0.001630721612903226,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.14066743850708, timestamp=1655499367.1597893) [('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: 144.08/144.08 result: MeasureResult(costs=(0.0016067480317460317,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1308460235595703, timestamp=1655547543.3468952) [('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: 0.001979
+ Time cost of this operator: 0.002044
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 5996480b7..3894ee7c1 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
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 320.1 98.77 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.948 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.914 0.282 (1, 1, 10, 10, 3) 1 1
- Total_time - 324.086 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.9 98.747 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.097 0.965 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.925 0.288 (1, 1, 10, 10, 3) 1 1
+ Total_time - 320.922 - - - -
@@ -397,10 +397,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 96.05 97.255 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.876 1.899 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.835 0.845 (1, 3, 10, 10, 1) 1 1
- Total_time - 98.761 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 153.3 98.271 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.775 1.138 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 0.59 (1, 1, 10, 10, 3) 1 1
+ Total_time - 155.997 - - - -
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 e9ec2d552..e97b9eaa6 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
@@ -224,7 +224,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpgba5o3yp/images/random'
+ '/tmp/tmpflj5o_4o/images/random'
@@ -324,8 +324,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpgba5o3yp/images/target contains 8144 images
- /tmp/tmpgba5o3yp/images/random contains 5000 images
+ /tmp/tmpflj5o_4o/images/target contains 8144 images
+ /tmp/tmpflj5o_4o/images/random contains 5000 images
@@ -500,13 +500,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2192 - accuracy: 0.9256 - val_loss: 0.1453 - val_accuracy: 0.9543
+ 328/328 - 54s - loss: 0.2134 - accuracy: 0.9271 - val_loss: 0.1380 - val_accuracy: 0.9585
Epoch 2/3
- 328/328 - 52s - loss: 0.1007 - accuracy: 0.9627 - val_loss: 0.1348 - val_accuracy: 0.9573
+ 328/328 - 52s - loss: 0.0972 - accuracy: 0.9639 - val_loss: 0.1234 - val_accuracy: 0.9607
Epoch 3/3
- 328/328 - 52s - loss: 0.0641 - accuracy: 0.9764 - val_loss: 0.1642 - val_accuracy: 0.9441
+ 328/328 - 52s - loss: 0.0673 - accuracy: 0.9752 - val_loss: 0.1572 - val_accuracy: 0.9479
- <keras.callbacks.History object at 0x7facc58f1210>
+ <keras.callbacks.History object at 0x7ff1e86f54d0>
@@ -863,7 +863,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 41.868 seconds)
+ **Total running time of the script:** ( 4 minutes 8.713 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 7d4d57f1f..f5b61a5f6 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**05:27.030** total execution time for **how_to_work_with_microtvm** files:
+**04:53.897** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:41.868 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:08.713 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.680 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.732 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.482 | 0.0 MB |
-+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.451 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``) | 00:00.000 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
++---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.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 8caa4ba2f..48ca9907a 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
=================
-**00:11.440** total execution time for **how_to_work_with_relay** files:
+**00:11.773** 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``) | 00:09.932 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.981 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.502 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.786 | 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 0d0f552c2..1c8386c24 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 0x7fac4475ea70>
+ <function my_cuda_math_rule at 0x7ff159c1d200>
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 4f1562dbb..649ee2f2b 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
=================
-**00:03.958** total execution time for **how_to_work_with_schedules** files:
+**00:04.189** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.858 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.930 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.922 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.512 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.539 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.498 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.520 | 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_extern_op.py` (``extern_op.py``) | 00:00.099 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.032 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.033 | 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``) | 00:00.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.012 | 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 0e01d52ef..01a6b2847 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/tmpo8sjud83/input0.cc'\nsource_filename = \"/tmp/tmpo8sjud83/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/tmpc4amql8y/input0.cc'\nsource_filename = \"/tmp/tmpc4amql8y/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 f206d3799..bd0072c96 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
=================
-**00:21.456** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.190** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.450 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.184 | 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 0eff8798d..f72216b9d 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 21.92s!
+ resnet18_v1 inference graph built in 21.90s!
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 08c9bb852..9242525ee 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:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.52s!
+ yolov3-tiny inference graph built in 15.22s!
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 6d7f0a5ab..258c20276 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
=================
-**01:29.609** total execution time for **topic_vta_tutorials_frontend** files:
+**01:29.517** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.590 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.240 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.019 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.277 | 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 a4217e3cc..fc4e5814a 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
=================
-**00:03.206** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.253** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.825 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.845 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.381 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.408 | 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 a2e2e2a04..b168f1fef 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
=================
-**00:00.663** total execution time for **topic_vta_tutorials** files:
+**00:00.713** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.342 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.363 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.321 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.350 | 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 0e638de50..ace899fc8 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: 93.982 ms
+ Execution time of this operator: 94.128 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 79d800240..d93858be4 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: 9.35/9.35 result: MeasureResult(costs=(0.028716855399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5912308692932129, timestamp=1655498227.4835176) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.70/9.35 result: MeasureResult(costs=(0.0993026256,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.737971544265747, timestamp=1655498229.7333903) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.0228017096,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6217353343963623, timestamp=1655498230.308111) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.59/11.77 result: MeasureResult(costs=(0.16856198579999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8178319931030273, timestamp=1655498233.662976) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.62/11.77 result: MeasureResult(costs=(0.0740766746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.31612229347229, timestamp=1655498235.1075253) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.79/11.77 result: MeasureResult(costs=(0.150043006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5395121574401855, timestamp=1655498238.1772516) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.77 result: MeasureResult(costs=(0.3078512572,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.041301965713501, timestamp=1655498243.266006) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.67/11.77 result: MeasureResult(costs=(0.0251541648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5451865196228027, timestamp=1655498243.832165) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.90/11.77 result: MeasureResult(costs=(0.1411295772,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3584036827087402, timestamp=1655498246.3086474) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.78/11.77 result: MeasureResult(costs=(0.0966992672,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6482198238372803, timestamp=1655498248.016553) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.57/9.57 result: MeasureResult(costs=(0.028064028400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5799887180328369, timestamp=1655546421.4435875) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.72/9.57 result: MeasureResult(costs=(0.0988507958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7334237098693848, timestamp=1655546423.687424) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.83/11.83 result: MeasureResult(costs=(0.022698381,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5857813358306885, timestamp=1655546424.2558951) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.74/11.83 result: MeasureResult(costs=(0.1539023714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5779600143432617, timestamp=1655546427.3689713) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.64/11.83 result: MeasureResult(costs=(0.0737395022,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3057539463043213, timestamp=1655546428.8032825) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.67/11.83 result: MeasureResult(costs=(0.1606874056,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.721618890762329, timestamp=1655546431.5740023) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.83 result: MeasureResult(costs=(0.3085565634,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.055051803588867, timestamp=1655546437.1731834) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.42/11.83 result: MeasureResult(costs=(0.025761548599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5520608425140381, timestamp=1655546437.7473106) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.60/11.83 result: MeasureResult(costs=(0.1677022536,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7814273834228516, timestamp=1655546440.647709) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.79/11.83 result: MeasureResult(costs=(0.0962706418,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6412205696105957, timestamp=1655546442.3491547) [('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 f9d4b6a2c..60110f50b 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': 492.91474093000033, 'median': 491.8427488500015, 'std': 2.815318947956547}
+ {'mean': 493.1380477699986, 'median': 492.5971845999811, 'std': 1.245634467347975}
@@ -550,31 +550,31 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:264: 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: 17.57/ 17.57 GFLOPS | Progress: (4/20) | 6.00 s
[Task 1/25] Current/Best: 6.16/ 17.57 GFLOPS | Progress: (8/20) | 8.95 s
[Task 1/25] Current/Best: 11.56/ 22.71 GFLOPS | Progress: (12/20) | 11.35 s
[Task 1/25] Current/Best: 16.79/ 22.80 GFLOPS | Progress: (16/20) | 13.02 s
[Task 1/25] Current/Best: 11.61/ 23.52 GFLOPS | Progress: (20/20) | 14.75 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.31/ 12.96 GFLOPS | Progress: (4/20) | 3.73 s
[Task 2/25] Current/Best: 13.84/ 18.62 GFLOPS | Progress: (8/20) | 5.01 s
[Task 2/25] Current/Best: 20.96/ 20.96 GFLOPS | Progress: (12/20) | 6.36 s
[Task 2/25] Current/Best: 11.79/ 20.96 GFLOPS | Progress: (16/20) | 7.62 s
[Task 2/25] Current/Best: 19.98/ 20.96 GFLOPS | Progress: (20/20) | 9.16 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/ 10.54 GFLOPS | Progress: (4/20) | 5.80 s
[Task 3/25] Current/Best: 15.57/ 16.84 GFLOPS | Progress: (8/20) | 7.73 s
[Task 3/25] Current/Best: 14.87/ 16.84 GFLOPS | Progress: (12/20) | 9.44 s
[Task 3/25] Current/Best: 7.18/ 23.72 GFLOPS | Progress: (16/20) | 11.34 s
[Task 3/25] Current/Best: 12.59/ 23.72 GFLOPS | Progress: (20/20) | 15.86 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.27/ 19.52 GFLOPS | Progress: (4/20) | 2.36 s
[Task 4/25] Current/Best: 6.86/ 19.52 GFLOPS | Progress: (8/20) | 6.66 s
[Task 4/25] Current/Best: 21.62/ 21.62 GFLOPS | Progress: (12/20) | 11.17 s
[Task 4/25] Current/Best: 17.14/ 21.62 GFLOPS | Progress: (16/20) | 13.37 s
[Task 4/25] Current/Best: 12.69/ 21.62 GFLOPS | Progress: (20/20) | 15.34 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.67/ 10.36 GFLOPS | Progress: (4/20) | 2.53 s
[Task 5/25] Current/Best: 11.87/ 12.78 GFLOPS | Progress: (8/20) | 4.59 s
[Task 5/25] Current/Best: 11.83/ 18.01 GFLOPS | Progress: (12/20) | 7.64 s
[Task 5/25] Current/Best: 11.77/ 22.66 GFLOPS | Progress: (16/20) | 9.04 s
[Task 5/25] Current/Best: 12.09/ 22.66 GFLOPS | Progress: (20/20) | 10.88 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.15/ 20.65 GFLOPS | Progress: (4/20) | 3.86 s
[Task 6/25] Current/Best: 19.01/ 20.65 GFLOPS | Progress: (8/20) | 5.62 s
[Task 6/25] Current/Best: 13.29/ 20.65 GFLOPS | Progress: (12/20) | 7.53 s
[Task 6/25] Current/Best: 20.02/ 20.65 GFLOPS | Progress: (16/20) | 9.80 s
[Task 6/25] Current/Best: 3.74/ 20.65 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: 11.24/ 12.85 GFLOPS | Progress: (4/20) | 3.53 s
[Task 7/25] Current/Best: 20.31/ 21.16 GFLOPS | Progress: (8/20) | 5.04 s
[Task 7/25] Current/Best: 16.13/ 21.16 GFLOPS | Progress: (12/20) | 6.96 s
[Task 7/25] Current/Best: 12.22/ 21.16 GFLOPS | Progress: (16/20) | 8.99 s
[Task 7/25] Current/Best: 6.36/ 21.62 GFLOPS | Progress: (20/20) | 11.44 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/ 14.34 GFLOPS | Progress: (4/20) | 2.83 s
[Task 8/25] Current/Best: 10.11/ 14.34 GFLOPS | Progress: (8/20) | 7.56 s
[Task 8/25] Current/Best: 12.69/ 14.34 GFLOPS | Progress: (12/20) | 13.63 s
[Task 8/25] Current/Best: 18.72/ 18.72 GFLOPS | Progress: (16/20) | 15.73 s
[Task 8/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (20/20) | 22.25 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.28/ 15.72 GFLOPS | Progress: (4/20) | 11.89 s
[Task 9/25] Current/Best: 23.04/ 23.04 GFLOPS | Progress: (8/20) | 13.72 s
[Task 9/25] Current/Best: 8.30/ 23.04 GFLOPS | Progress: (12/20) | 16.05 s
[Task 9/25] Current/Best: 18.07/ 23.04 GFLOPS | Progress: (16/20) | 18.69 s
[Task 9/25] Current/Best: 9.05/ 23.04 GFLOPS | Progress: (20/20) | 26.32 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (4/20) | 2.50 s
[Task 10/25] Current/Best: 15.44/ 18.23 GFLOPS | Progress: (8/20) | 4.08 s
[Task 10/25] Current/Best: 12.60/ 19.03 GFLOPS | Progress: (12/20) | 5.59 s
[Task 10/25] Current/Best: 19.19/ 20.19 GFLOPS | Progress: (16/20) | 6.69 s
[Task 10/25] Current/Best: 8.86/ 20.19 GFLOPS | Progress: (20/20
) | 8.21 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.36/ 18.11 GFLOPS | Progress: (4/20) | 3.27 s
[Task 11/25] Current/Best: 15.39/ 18.11 GFLOPS | Progress: (8/20) | 6.01 s
[Task 11/25] Current/Best: 17.83/ 18.11 GFLOPS | Progress: (12/20) | 8.06 s
[Task 11/25] Current/Best: 13.39/ 21.18 GFLOPS | Progress: (16/20) | 10.83 s
[Task 11/25] Current/Best: 19.47/ 21.57 GFLOPS | Progress: (20/20) | 12.85 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.84/ 18.08 GFLOPS | Progress: (4/20) | 5.27 s
[Task 12/25] Current/Best: 5.27/ 18.08 GFLOPS | Progress: (8/20) | 8.92 s
[Task 12/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (12/20) | 10.90 s
[Task 12/25] Current/Best: 15.37/ 18.95 GFLOPS | Progress: (16/20) | 13.63 s
[Task 12/25] Current/Best: 15.10/ 18.95 GFLOPS | Progress: (20/20) | 15.55 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.66/ 17.27 GFLOPS | Progress: (4/20) | 3.57 s
[Task 13/25] Current/Best: 16.12/ 21.08 GFLOPS | Progress: (8/20) | 5.97 s
[Task 13/25] Current/Best: 19.64/ 21.37 GFLOPS | Progress: (12/20) | 8.88 s
[Task 13/25] Current/Best: 12.24/ 21.37 GFLOPS | Progress: (16/20) | 12.27 s
[Task 13/25] Current/Best: 18.76/ 21.37 GFLOPS | Progress: (20/20) | 14.53 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) | 3.25 s
[Task 14/25] Current/Best: 6.02/ 13.57 GFLOPS | Progress: (8/20) | 5.41 s
[Task 14/25] Current/Best: 21.19/ 21.19 GFLOPS | Progress: (12/20) | 7.95 s
[Task 14/25] Current/Best: 16.21/ 21.19 GFLOPS | Progress: (16/20) | 9.63 s Done.
-
[Task 14/25] Current/Best: 17.12/ 21.19 GFLOPS | Progress: (20/20) | 11.34 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.13/ 17.63 GFLOPS | Progress: (4/20) | 2.61 s
[Task 15/25] Current/Best: 14.50/ 18.06 GFLOPS | Progress: (8/20) | 3.89 s
[Task 15/25] Current/Best: 10.38/ 22.31 GFLOPS | Progress: (12/20) | 5.91 s
[Task 15/25] Current/Best: 20.42/ 22.31 GFLOPS | Progress: (16/20) | 8.90 s
[Task 15/25] Current/Best: 9.69/ 22.31 GFLOPS | Progress: (20/20) | 9.91 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.52/ 20.52 GFLOPS | Progress: (4/20) | 2.86 s
[Task 16/25] Current/Best: 3.04/ 20.52 GFLOPS | Progress: (8/20) | 4.48 s
[Task 16/25] Current/Best: 19.84/ 20.52 GFLOPS | Progress: (12/20) | 5.69 s
[Task 16/25] Current/Best: 17.84/ 20.52 GFLOPS | Progress: (16/20) |
7.02 s
[Task 16/25] Current/Best: 10.06/ 22.33 GFLOPS | Progress: (20/20) | 9.06 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 11.83/ 18.87 GFLOPS | Progress: (4/20) | 4.70 s
[Task 17/25] Current/Best: 14.38/ 23.09 GFLOPS | Progress: (8/20) | 7.57 s
[Task 17/25] Current/Best: 16.92/ 23.09 GFLOPS | Progress: (12/20) | 9.61 s
[Task 17/25] Current/Best: 16.50/ 23.09 GFLOPS | Progress: (16/20) | 11.72 s
[Task 17/25] Current/Best: 10.04/ 23.09 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: 11.42/ 17.81 GFLOPS | Progress: (4/20) | 3.60 s
[Task 18/25] Current/Best: 10.59/ 20.06 GFLOPS | Progress: (8/20) | 7.04 s
[Task 18/25] Current/Best: 19.43/ 20.06 GFLOPS | Progress: (12/20) | 8.98 s
[Task 18/25] Current/Best: 9.96/ 20.06 GFLOPS | Progress: (16/20) | 12.55 s
[Task 18/25] Current/Best: 20.64/ 20.64 GFLOPS | Progress: (20/20) | 14.07 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.03/ 20.31 GFLOPS | Progress: (4/20) | 5.97 s
[Task 19/25] Current/Best: 2.60/ 20.31 GFLOPS | Progress: (8/20) | 9.25 s
[Task 19/25] Current/Best: 19.48/ 20.88 GFLOPS | Progress: (12/20) | 12.02 s
[Task 19/25] Current/Best: 15.36/ 21.38 GFLOPS | Progress: (16/20) | 14.85 s
[Task 19/25] Current/Best: 2.70/ 23.08 GFLOPS | Progress: (20/20) | 17.62 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.98/ 15.07 GFLOPS | Progress: (4/20) | 3.27 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.56/ 17.56 GFLOPS | Progress: (4/20) | 5.59 s
[Task 1/25] Current/Best: 6.16/ 17.56 GFLOPS | Progress: (8/20) | 8.94 s
[Task 1/25] Current/Best: 11.55/ 22.83 GFLOPS | Progress: (12/20) | 11.35 s
[Task 1/25] Current/Best: 16.77/ 22.83 GFLOPS | Progress: (16/20) | 13.02 s
[Task 1/25] Current/Best: 11.65/ 23.92 GFLOPS | Progress: (20/20) | 14.75 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.34/ 13.01 GFLOPS | Progress: (4/20) | 3.72 s
[Task 2/25] Current/Best: 14.15/ 18.09 GFLOPS | Progress: (8/20) | 5.01 s
[Task 2/25] Current/Best: 21.29/ 21.29 GFLOPS | Progress: (12/20) | 6.32 s
[Task 2/25] Current/Best: 12.53/ 21.29 GFLOPS | Progress: (16/20) | 7.60 s
[Task 2/25] Current/Best: 18.96/ 21.29 GFLOPS | Progress: (20/20) | 9.17 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/ 10.56 GFLOPS | Progress: (4/20) | 5.82 s
[Task 3/25] Current/Best: 15.60/ 16.94 GFLOPS | Progress: (8/20) | 7.72 s
[Task 3/25] Current/Best: 14.89/ 16.94 GFLOPS | Progress: (12/20) | 9.42 s
[Task 3/25] Current/Best: 7.19/ 23.82 GFLOPS | Progress: (16/20) | 11.31 s
[Task 3/25] Current/Best: 11.23/ 23.82 GFLOPS | Progress: (20/20) | 15.85 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.48/ 20.42 GFLOPS | Progress: (4/20) | 2.31 s
[Task 4/25] Current/Best: 6.39/ 20.42 GFLOPS | Progress: (8/20) | 6.58 s
[Task 4/25] Current/Best: 21.73/ 21.73 GFLOPS | Progress: (12/20) | 11.11 s
[Task 4/25] Current/Best: 16.74/ 21.73 GFLOPS | Progress: (16/20) | 13.31 s
[Task 4/25] Current/Best: 13.41/ 21.73 GFLOPS | Progress: (20/20) | 15.32 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.56/ 10.32 GFLOPS | Progress: (4/20) | 2.57 s
[Task 5/25] Current/Best: 11.65/ 12.73 GFLOPS | Progress: (8/20) | 4.63 s
[Task 5/25] Current/Best: 11.75/ 17.87 GFLOPS | Progress: (12/20) | 7.53 s
[Task 5/25] Current/Best: 11.86/ 22.72 GFLOPS | Progress: (16/20) | 8.93 s
[Task 5/25] Current/Best: 12.05/ 22.72 GFLOPS | Progress: (20/20) | 10.78 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.16/ 20.80 GFLOPS | Progress: (4/20) | 3.88 s
[Task 6/25] Current/Best: 19.05/ 20.80 GFLOPS | Progress: (8/20) | 5.63 s
[Task 6/25] Current/Best: 13.25/ 20.80 GFLOPS | Progress: (12/20) | 7.56 s
[Task 6/25] Current/Best: 20.04/ 20.80 GFLOPS | Progress: (16/20) | 9.78 s
[Task 6/25] Current/Best: 3.72/ 20.80 GFLOPS | Progress: (20/20) | 12.28 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.23/ 12.93 GFLOPS | Progress: (4/20) | 3.52 s
[Task 7/25] Current/Best: 20.25/ 21.18 GFLOPS | Progress: (8/20) | 5.02 s
[Task 7/25] Current/Best: 15.94/ 21.18 GFLOPS | Progress: (12/20) | 6.90 s
[Task 7/25] Current/Best: 12.25/ 21.18 GFLOPS | Progress: (16/20) | 8.92 s
[Task 7/25] Current/Best: 6.30/ 21.82 GFLOPS | Progress: (20/20) | 11.36 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.97/ 14.24 GFLOPS | Progress: (4/20) | 2.85 s
[Task 8/25] Current/Best: 9.43/ 14.24 GFLOPS | Progress: (8/20) | 7.59 s
[Task 8/25] Current/Best: 12.74/ 14.24 GFLOPS | Progress: (12/20) | 13.69 s
[Task 8/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (16/20) | 15.76 s
[Task 8/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (20/20) | 22.20 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/ 14.36 GFLOPS | Progress: (4/20) | 11.91 s
[Task 9/25] Current/Best: 23.56/ 23.56 GFLOPS | Progress: (8/20) | 13.67 s
[Task 9/25] Current/Best: 8.27/ 23.56 GFLOPS | Progress: (12/20) | 16.02 s
[Task 9/25] Current/Best: 17.83/ 23.56 GFLOPS | Progress: (16/20) | 18.55 s
[Task 9/25] Current/Best: 9.08/ 23.56 GFLOPS | Progress: (20/20) | 26.10 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (4/20) | 2.48 s
[Task 10/25] Current/Best: 15.54/ 18.22 GFLOPS | Progress: (8/20) | 4.04 s
[Task 10/25] Current/Best: 11.81/ 18.95 GFLOPS | Progress: (12/20) | 5.57 s
[Task 10/25] Current/Best: 19.11/ 20.35 GFLOPS | Progress: (16/20) | 6.66 s
[Task 10/25] Current/Best: 8.82/ 20.35 GFLOPS | Progress: (20/20
) | 8.18 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.24/ 18.12 GFLOPS | Progress: (4/20) | 3.26 s
[Task 11/25] Current/Best: 16.74/ 18.12 GFLOPS | Progress: (8/20) | 5.99 s
[Task 11/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (12/20) | 8.03 s
[Task 11/25] Current/Best: 13.48/ 21.18 GFLOPS | Progress: (16/20) | 10.77 s
[Task 11/25] Current/Best: 19.51/ 21.51 GFLOPS | Progress: (20/20) | 12.78 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.81/ 17.96 GFLOPS | Progress: (4/20) | 5.21 s
[Task 12/25] Current/Best: 5.27/ 17.96 GFLOPS | Progress: (8/20) | 8.83 s
[Task 12/25] Current/Best: 18.52/ 18.75 GFLOPS | Progress: (12/20) | 10.81 s
[Task 12/25] Current/Best: 15.34/ 18.75 GFLOPS | Progress: (16/20) | 13.57 s
[Task 12/25] Current/Best: 15.17/ 18.75 GFLOPS | Progress: (20/20) | 15.52 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.74/ 17.34 GFLOPS | Progress: (4/20) | 3.56 s
[Task 13/25] Current/Best: 15.92/ 21.04 GFLOPS | Progress: (8/20) | 5.98 s
[Task 13/25] Current/Best: 19.76/ 21.83 GFLOPS | Progress: (12/20) | 8.83 s
[Task 13/25] Current/Best: 12.28/ 21.83 GFLOPS | Progress: (16/20) | 12.21 s
[Task 13/25] Current/Best: 18.67/ 21.83 GFLOPS | Progress: (20/20) | 14.48 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.73/ 13.73 GFLOPS | Progress: (4/20) | 3.24 s
[Task 14/25] Current/Best: 6.10/ 13.73 GFLOPS | Progress: (8/20) | 5.42 s
[Task 14/25] Current/Best: 20.29/ 20.29 GFLOPS | Progress: (12/20) | 7.96 s
[Task 14/25] Current/Best: 16.82/ 20.29 GFLOPS | Progress: (16/20) | 9.63 s Done.
+
[Task 14/25] Current/Best: 17.23/ 20.29 GFLOPS | Progress: (20/20) | 11.34 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.18/ 17.69 GFLOPS | Progress: (4/20) | 2.65 s
[Task 15/25] Current/Best: 13.12/ 18.06 GFLOPS | Progress: (8/20) | 3.94 s
[Task 15/25] Current/Best: 10.37/ 22.28 GFLOPS | Progress: (12/20) | 5.99 s
[Task 15/25] Current/Best: 20.28/ 22.28 GFLOPS | Progress: (16/20) | 9.42 s
[Task 15/25] Current/Best: 9.66/ 22.28 GFLOPS | Progress: (20/20) | 10.43 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.60/ 20.60 GFLOPS | Progress: (4/20) | 2.94 s
[Task 16/25] Current/Best: 3.04/ 20.60 GFLOPS | Progress: (8/20) | 4.54 s
[Task 16/25] Current/Best: 19.41/ 20.60 GFLOPS | Progress: (12/20) | 5.75 s
[Task 16/25] Current/Best: 17.46/ 20.60 GFLOPS | Progress: (16/20) |
7.07 s
[Task 16/25] Current/Best: 10.14/ 22.34 GFLOPS | Progress: (20/20) | 9.10 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.18/ 18.85 GFLOPS | Progress: (4/20) | 4.68 s
[Task 17/25] Current/Best: 14.37/ 23.33 GFLOPS | Progress: (8/20) | 7.41 s
[Task 17/25] Current/Best: 17.21/ 23.33 GFLOPS | Progress: (12/20) | 9.46 s
[Task 17/25] Current/Best: 16.52/ 23.33 GFLOPS | Progress: (16/20) | 11.57 s
[Task 17/25] Current/Best: 10.04/ 23.33 GFLOPS | Progress: (20/20) | 13.68 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.30/ 17.35 GFLOPS | Progress: (4/20) | 3.63 s
[Task 18/25] Current/Best: 10.54/ 18.91 GFLOPS | Progress: (8/20) | 7.05 s
[Task 18/25] Current/Best: 18.58/ 18.91 GFLOPS | Progress: (12/20) | 8.99 s
[Task 18/25] Current/Best: 10.10/ 18.91 GFLOPS | Progress: (16/20) | 12.50 s
[Task 18/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (20/20) | 14.00 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.17/ 20.45 GFLOPS | Progress: (4/20) | 5.91 s
[Task 19/25] Current/Best: 2.61/ 20.45 GFLOPS | Progress: (8/20) | 9.16 s
[Task 19/25] Current/Best: 18.67/ 21.88 GFLOPS | Progress: (12/20) | 11.97 s
[Task 19/25] Current/Best: 13.49/ 21.98 GFLOPS | Progress: (16/20) | 14.81 s
[Task 19/25] Current/Best: 2.70/ 23.64 GFLOPS | Progress: (20/20) | 17.62 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.27/ 15.38 GFLOPS | Progress: (4/20) | 3.24 s Done.
Done.
-
[Task 20/25] Current/Best: 9.73/ 15.07 GFLOPS | Progress: (8/20) | 6.55 s
[Task 20/25] Current/Best: 2.32/ 16.56 GFLOPS | Progress: (12/20) | 10.42 s
[Task 20/25] Current/Best: 12.52/ 16.56 GFLOPS | Progress: (16/20) | 14.00 s
[Task 20/25] Current/Best: 12.77/ 21.83 GFLOPS | Progress: (20/20) | 16.13 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.63 GFLOPS | Progress: (4/20) | 3.17 s
[Task 21/25] Current/Best: 14.58/ 17.63 GFLOPS | Progress: (8/20) | 4.74 s
[Task 21/25] Current/Best: 1.61/ 17.63 GFLOPS | Progress: (12/20) | 6.85 s
[Task 21/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (16/20) | 10.28 s
[Task 21/25] Current/Best: 4.47/ 18.23 GFLOPS | Progress: (20/20) | 17.33 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.02 GFLOPS | Progress: (4/20
) | 2.61 s
[Task 22/25] Current/Best: 8.71/ 21.92 GFLOPS | Progress: (8/20) | 4.59 s
[Task 22/25] Current/Best: 19.99/ 21.92 GFLOPS | Progress: (12/20) | 6.87 s
[Task 22/25] Current/Best: 14.95/ 21.92 GFLOPS | Progress: (16/20) | 8.91 s
[Task 22/25] Current/Best: 14.19/ 21.92 GFLOPS | Progress: (20/20) | 10.62 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.49/ 20.69 GFLOPS | Progress: (4/20) | 3.16 s
[Task 23/25] Current/Best: 15.20/ 20.69 GFLOPS | Progress: (8/20) | 6.52 s
[Task 23/25] Current/Best: 20.95/ 21.66 GFLOPS | Progress: (12/20) | 8.33 s
[Task 23/25] Current/Best: 6.43/ 21.66 GFLOPS | Progress: (16/20) | 15.21 s
[Task 23/25] Current/Best: 7.73/ 21.66 GFLOPS | Progress: (20/20) | 19.44 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.17/ 8.17 GFLOPS | Progress: (4/20) | 11.74 s
[Task 24/25] Current/Best: 2.15/ 8.17 GFLOPS | Progress: (8/20) | 22.71 s
[Task 24/25] Current/Best: 4.51/ 8.17 GFLOPS | Progress: (12/20) | 34.18 s Done.
+
[Task 20/25] Current/Best: 9.92/ 15.38 GFLOPS | Progress: (8/20) | 6.64 s
[Task 20/25] Current/Best: 2.32/ 16.53 GFLOPS | Progress: (12/20) | 10.57 s
[Task 20/25] Current/Best: 11.10/ 16.53 GFLOPS | Progress: (16/20) | 14.11 s
[Task 20/25] Current/Best: 12.85/ 22.26 GFLOPS | Progress: (20/20) | 16.20 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.76 GFLOPS | Progress: (4/20) | 3.14 s
[Task 21/25] Current/Best: 14.66/ 17.76 GFLOPS | Progress: (8/20) | 4.70 s
[Task 21/25] Current/Best: 1.61/ 17.76 GFLOPS | Progress: (12/20) | 6.80 s
[Task 21/25] Current/Best: 18.17/ 18.17 GFLOPS | Progress: (16/20) | 10.19 s
[Task 21/25] Current/Best: 4.47/ 18.17 GFLOPS | Progress: (20/20) | 17.22 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.08 GFLOPS | Progress: (4/20
) | 2.61 s
[Task 22/25] Current/Best: 8.75/ 22.07 GFLOPS | Progress: (8/20) | 4.49 s
[Task 22/25] Current/Best: 20.08/ 22.07 GFLOPS | Progress: (12/20) | 6.76 s
[Task 22/25] Current/Best: 14.99/ 22.07 GFLOPS | Progress: (16/20) | 8.82 s
[Task 22/25] Current/Best: 14.15/ 22.07 GFLOPS | Progress: (20/20) | 10.52 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.69/ 20.80 GFLOPS | Progress: (4/20) | 3.15 s
[Task 23/25] Current/Best: 14.43/ 20.80 GFLOPS | Progress: (8/20) | 6.48 s
[Task 23/25] Current/Best: 20.98/ 21.85 GFLOPS | Progress: (12/20) | 8.25 s
[Task 23/25] Current/Best: 6.51/ 21.85 GFLOPS | Progress: (16/20) | 15.23 s
[Task 23/25] Current/Best: 8.04/ 21.85 GFLOPS | Progress: (20/20) | 19.41 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.04/ 8.04 GFLOPS | Progress: (4/20) | 11.69 s
[Task 24/25] Current/Best: 3.62/ 8.04 GFLOPS | Progress: (8/20) | 22.94 s
[Task 24/25] Current/Best: 4.42/ 8.04 GFLOPS | Progress: (12/20) | 33.64 s Done.
Done.
-
[Task 24/25] Current/Best: 6.37/ 8.82 GFLOPS | Progress: (16/20) | 39.60 s
[Task 24/25] Current/Best: 3.31/ 8.85 GFLOPS | Progress: (20/20) | 45.50 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/ 2.94 GFLOPS | Progress: (4/20) | 11.53 s
[Task 25/25] Current/Best: 5.90/ 8.00 GFLOPS | Progress: (8/20) | 22.75 s
[Task 25/25] Current/Best: 5.90/ 8.00 GFLOPS | Progress: (12/20) | 34.02 s
[Task 25/25] Current/Best: 5.77/ 9.26 GFLOPS | Progress: (16/20) | 35.72 s
[Task 25/25] Current/Best: 2.85/ 9.26 GFLOPS | Progress: (20/20) | 46.39 s
+
[Task 24/25] Current/Best: 5.86/ 8.83 GFLOPS | Progress: (16/20) | 39.01 s
[Task 24/25] Current/Best: 3.37/ 9.20 GFLOPS | Progress: (20/20) | 44.88 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/ 2.82 GFLOPS | Progress: (4/20) | 11.52 s
[Task 25/25] Current/Best: 6.27/ 8.24 GFLOPS | Progress: (8/20) | 22.72 s
[Task 25/25] Current/Best: 6.15/ 8.24 GFLOPS | Progress: (12/20) | 33.98 s
[Task 25/25] Current/Best: 5.96/ 8.78 GFLOPS | Progress: (16/20) | 35.77 s
[Task 25/25] Current/Best: 2.87/ 9.63 GFLOPS | Progress: (20/20) | 46.42 s
@@ -735,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 412.12751948999994, 'median': 412.04843069999697, 'std': 0.6459348994910754}
- unoptimized: {'mean': 492.91474093000033, 'median': 491.8427488500015, 'std': 2.815318947956547}
+ optimized: {'mean': 407.95035273001304, 'median': 407.77613870000096, 'std': 0.9025302456285362}
+ unoptimized: {'mean': 493.1380477699986, 'median': 492.5971845999811, 'std': 1.245634467347975}
@@ -759,7 +759,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 10.323 seconds)
+ **Total running time of the script:** ( 10 minutes 11.814 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 07545f1e5..81ad03cce 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
- 1.245e-07 secs/op
+ 1.339e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index ca97faf01..769102265 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, 0x2164a6d0)), stage(b, placeholder(b, 0x216949b0)), 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, 0xc710720)), stage(b, placeholder(b, 0xbbd1d90)), 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 f99bcd44f..951c0b8b3 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,29 +5,29 @@
Computation times
=================
-**12:54.300** total execution time for **tutorial** files:
+**12:49.553** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:10.323 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:11.814 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.759 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.723 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:51.420 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:43.460 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:27.828 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:27.696 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.881 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.226 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.279 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.809 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.667 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.670 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.143 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.156 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.000 | 0.0 MB |
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 453a09a91..139d1398b 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:264: 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 8.051810000324622e-06 1.0
- naive 5.852099999999999e-06 0.7268055256847916
- parallel 6.0782000000000005e-06 0.7548861684211311
- vector 2.45766e-05 3.0523074934715493
+ numpy 8.158410000760341e-06 1.0
+ naive 5.846500000000001e-06 0.7166224790682404
+ parallel 6.9463e-06 0.8514281581034324
+ vector 2.4548100000000003e-05 3.0089318871829422
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018632
+ Numpy running time: 0.017844
@@ -983,7 +983,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:264: 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: 3.235045
+ none: 3.409536
@@ -1088,7 +1088,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:264: 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: 0.296574
+ blocking: 0.297843
@@ -1186,7 +1186,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:264: 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: 0.334723
+ vectorization: 0.332657
@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:264: 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: 0.116859
+ loop permutation: 0.120565
@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:264: 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: 0.111147
+ array packing: 0.111045
@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:264: 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: 0.110734
+ block caching: 0.111168
@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:264: 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: 0.144874
+ parallelization: 0.145184
@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 3.2350452699 1.0
- blocking 0.29657368110000004 0.09167528005231518
- vectorization 0.3347226748 0.10346769422807699
- loop permutation 0.11685929129999999 0.03612292303520447
- array packing 0.11114693410000001 0.034357149537952436
- block caching 0.11073384319999999 0.03422945707446713
- parallelization 0.1448742241 0.04478275016673206
+ none 3.4095355486 1.0
+ blocking 0.2978434897 0.08735603000892554
+ vectorization 0.33265705840000004 0.09756667841066897
+ loop permutation 0.12056504679999999 0.03536113499374001
+ array packing 0.1110453093 0.03256904282625728
+ block caching 0.11116820680000002 0.03260508805829789
+ parallelization 0.1451835296 0.042581614865289864
@@ -1673,6 +1673,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 0.723 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 8af40dc72..38195835d 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-2708b6ca024d8e328151d9beb237b9852093cff6
+f8b320f523b24fd8ddb8cf7026e61bbb4f4ea348
diff --git a/docs/contribute/pull_request.html b/docs/contribute/pull_request.html
index 41077a99d..8a8e10e21 100644
--- a/docs/contribute/pull_request.html
+++ b/docs/contribute/pull_request.html
@@ -428,6 +428,13 @@ python tests/scripts/ci.py cpu --skip-build --tests tests/python/unittest/test_t
python tests/scripts/ci.py cpu --interactive
</pre></div>
</div>
+<p>We regularly update our docker images and, over time, stale images may unnecessarily consume disk
+space. You can remove stale images that aren’t used in the presently checked-out branch plus any
+other worktrees using the following command:</p>
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>docker/clear-stale-images.sh
+</pre></div>
+</div>
+<p>Consult the <code class="docutils literal notranslate"><span class="pre">--help</span></code> for more options.</p>
</div>
<div class="section" id="c-local">
<h3><a class="toc-backref" href="#id5">C++ (local)</a><a class="headerlink" href="#c-local" title="Permalink to this headline">¶</a></h3>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 640fd0bb8..123c56871 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -403,7 +403,7 @@ 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.zip1f2109f5-9cd0-45c3-bfe6-371a0c53d0b9 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.zip185cf734-9ebd-4a95-aac6-c0c3dda4d326 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 3f58778b5..b1c2c0d8b 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -408,40 +408,51 @@ 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<07:42, 94.0kB/s]
- 0%| | 48.0k/41.5M [00:00<04:52, 149kB/s]
- 0%| | 96.0k/41.5M [00:00<03:27, 209kB/s]
- 0%| | 192k/41.5M [00:00<02:04, 348kB/s]
- 1%| | 400k/41.5M [00:00<01:05, 661kB/s]
- 2%|1 | 808k/41.5M [00:01<00:34, 1.25MB/s]
- 4%|3 | 1.59M/41.5M [00:01<00:17, 2.40MB/s]
- 7%|7 | 3.07M/41.5M [00:01<00:09, 4.46MB/s]
- 11%|# | 4.55M/41.5M [00:01<00:06, 5.84MB/s]
- 15%|#4 | 6.03M/41.5M [00:01<00:05, 6.76MB/s]
- 18%|#8 | 7.52M/41.5M [00:01<00:04, 7.41MB/s]
- 22%|##1 | 8.99M/41.5M [00:02<00:04, 7.84MB/s]
- 25%|##5 | 10.5M/41.5M [00:02<00:03, 8.14MB/s]
- 29%|##8 | 11.9M/41.5M [00:02<00:03, 8.33MB/s]
- 32%|###2 | 13.4M/41.5M [00:02<00:03, 8.50MB/s]
- 36%|###5 | 14.9M/41.5M [00:02<00:03, 8.61MB/s]
- 39%|###9 | 16.4M/41.5M [00:02<00:03, 8.68MB/s]
- 43%|####3 | 17.9M/41.5M [00:03<00:02, 8.74MB/s]
- 47%|####6 | 19.4M/41.5M [00:03<00:02, 8.78MB/s]
- 50%|##### | 20.8M/41.5M [00:03<00:02, 8.79MB/s]
- 54%|#####3 | 22.3M/41.5M [00:03<00:02, 8.82MB/s]
- 57%|#####7 | 23.8M/41.5M [00:03<00:02, 8.84MB/s]
- 61%|###### | 25.3M/41.5M [00:04<00:01, 8.84MB/s]
- 64%|######4 | 26.8M/41.5M [00:04<00:01, 8.83MB/s]
- 68%|######8 | 28.2M/41.5M [00:04<00:01, 8.83MB/s]
- 72%|#######1 | 29.7M/41.5M [00:04<00:01, 8.85MB/s]
- 75%|#######5 | 31.2M/41.5M [00:04<00:01, 8.83MB/s]
- 79%|#######8 | 32.6M/41.5M [00:04<00:01, 8.80MB/s]
- 82%|########2 | 34.1M/41.5M [00:05<00:00, 8.80MB/s]
- 86%|########5 | 35.6M/41.5M [00:05<00:00, 8.82MB/s]
- 89%|########9 | 37.1M/41.5M [00:05<00:00, 8.81MB/s]
- 93%|#########2| 38.5M/41.5M [00:05<00:00, 8.82MB/s]
- 96%|#########6| 40.0M/41.5M [00:05<00:00, 8.83MB/s]
-100%|##########| 41.5M/41.5M [00:05<00:00, 7.50MB/s]
+ 0%| | 16.0k/41.5M [00:00<07:46, 93.3kB/s]
+ 0%| | 48.0k/41.5M [00:00<04:54, 148kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:29, 207kB/s]
+ 0%| | 160k/41.5M [00:00<02:39, 272kB/s]
+ 1%| | 280k/41.5M [00:00<01:41, 424kB/s]
+ 1%|1 | 520k/41.5M [00:01<00:57, 753kB/s]
+ 2%|2 | 944k/41.5M [00:01<00:32, 1.31MB/s]
+ 4%|4 | 1.82M/41.5M [00:01<00:16, 2.59MB/s]
+ 8%|7 | 3.30M/41.5M [00:01<00:07, 5.08MB/s]
+ 10%|# | 4.34M/41.5M [00:01<00:06, 5.73MB/s]
+ 14%|#4 | 5.82M/41.5M [00:01<00:05, 6.75MB/s]
+ 18%|#7 | 7.28M/41.5M [00:02<00:04, 7.37MB/s]
+ 21%|##1 | 8.76M/41.5M [00:02<00:03, 8.95MB/s]
+ 23%|##3 | 9.69M/41.5M [00:02<00:04, 7.98MB/s]
+ 26%|##5 | 10.7M/41.5M [00:02<00:03, 8.30MB/s]
+ 28%|##8 | 11.7M/41.5M [00:02<00:03, 7.99MB/s]
+ 32%|###1 | 13.2M/41.5M [00:02<00:03, 9.56MB/s]
+ 34%|###4 | 14.2M/41.5M [00:02<00:03, 8.40MB/s]
+ 36%|###6 | 15.1M/41.5M [00:02<00:03, 8.44MB/s]
+ 39%|###8 | 16.1M/41.5M [00:03<00:03, 8.18MB/s]
+ 42%|####2 | 17.6M/41.5M [00:03<00:02, 9.84MB/s]
+ 45%|####4 | 18.6M/41.5M [00:03<00:02, 8.50MB/s]
+ 47%|####7 | 19.6M/41.5M [00:03<00:02, 8.49MB/s]
+ 50%|####9 | 20.6M/41.5M [00:03<00:02, 8.21MB/s]
+ 53%|#####3 | 22.0M/41.5M [00:03<00:02, 9.80MB/s]
+ 55%|#####5 | 23.0M/41.5M [00:03<00:02, 8.47MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:04<00:02, 8.54MB/s]
+ 60%|###### | 25.0M/41.5M [00:04<00:02, 8.27MB/s]
+ 64%|######3 | 26.4M/41.5M [00:04<00:01, 9.77MB/s]
+ 66%|######6 | 27.4M/41.5M [00:04<00:01, 8.43MB/s]
+ 68%|######8 | 28.4M/41.5M [00:04<00:01, 8.74MB/s]
+ 71%|####### | 29.4M/41.5M [00:04<00:01, 9.18MB/s]
+ 73%|#######3 | 30.4M/41.5M [00:04<00:01, 8.43MB/s]
+ 76%|#######5 | 31.4M/41.5M [00:04<00:01, 8.75MB/s]
+ 78%|#######8 | 32.4M/41.5M [00:04<00:01, 9.18MB/s]
+ 80%|######## | 33.3M/41.5M [00:05<00:01, 8.38MB/s]
+ 83%|########2 | 34.3M/41.5M [00:05<00:00, 8.75MB/s]
+ 85%|########5 | 35.4M/41.5M [00:05<00:00, 8.60MB/s]
+ 87%|########7 | 36.2M/41.5M [00:05<00:00, 8.39MB/s]
+ 90%|########9 | 37.3M/41.5M [00:05<00:00, 8.77MB/s]
+ 92%|#########2| 38.3M/41.5M [00:05<00:00, 8.78MB/s]
+ 94%|#########4| 39.2M/41.5M [00:05<00:00, 8.53MB/s]
+ 97%|#########6| 40.2M/41.5M [00:05<00:00, 9.01MB/s]
+ 99%|#########9| 41.3M/41.5M [00:06<00:00, 9.42MB/s]
+100%|##########| 41.5M/41.5M [00:06<00:00, 7.13MB/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 9ed51f1f6..053ec392f 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -469,7 +469,7 @@ 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 6.200 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.750 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 5e35da1e7..ceecd802e 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -390,9 +390,9 @@ 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]
- 20%|## | 8.96M/44.7M [00:00<00:00, 87.7MB/s]
- 61%|###### | 27.2M/44.7M [00:00<00:00, 147MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 154MB/s]
+ 37%|###7 | 16.6M/44.7M [00:00<00:00, 174MB/s]
+ 91%|######### | 40.4M/44.7M [00:00<00:00, 219MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 215MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index df5d96a5f..e02d5d4c6 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>05:17.787</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:20.514</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -312,43 +312,43 @@
</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>01:06.200</p></td>
+<td><p>01:07.750</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>00:59.486</p></td>
+<td><p>00:59.629</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>00:56.749</p></td>
+<td><p>00:56.952</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>00:31.079</p></td>
+<td><p>00:31.303</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>00:23.890</p></td>
+<td><p>00:24.364</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>00:22.456</p></td>
+<td><p>00:23.221</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>00:22.056</p></td>
+<td><p>00:21.849</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>00:19.013</p></td>
+<td><p>00:19.006</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>00:14.529</p></td>
+<td><p>00:14.068</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>00:02.329</p></td>
+<td><p>00:02.372</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 83edeb1c3..7b523ea21 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -629,7 +629,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.8340 15.8128 15.9222 15.7389 0.0611
+ 15.8829 15.8845 16.2002 15.6726 0.1733
</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 a6b201344..d7d2b7cf5 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -412,15 +412,14 @@ 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]
- 9%|9 | 15.4M/170M [00:00<00:01, 161MB/s]
- 21%|##1 | 36.1M/170M [00:00<00:00, 194MB/s]
- 33%|###2 | 55.8M/170M [00:00<00:00, 200MB/s]
- 45%|####5 | 77.1M/170M [00:00<00:00, 209MB/s]
- 59%|#####8 | 99.5M/170M [00:00<00:00, 218MB/s]
- 72%|#######1 | 122M/170M [00:00<00:00, 224MB/s]
- 85%|########4 | 144M/170M [00:00<00:00, 226MB/s]
- 98%|#########7| 166M/170M [00:00<00:00, 228MB/s]
-100%|##########| 170M/170M [00:00<00:00, 218MB/s]
+ 7%|7 | 12.1M/170M [00:00<00:01, 127MB/s]
+ 20%|## | 34.2M/170M [00:00<00:00, 188MB/s]
+ 36%|###5 | 60.6M/170M [00:00<00:00, 229MB/s]
+ 51%|#####1 | 87.0M/170M [00:00<00:00, 248MB/s]
+ 67%|######6 | 113M/170M [00:00<00:00, 258MB/s]
+ 82%|########2 | 140M/170M [00:00<00:00, 265MB/s]
+ 98%|#########7| 166M/170M [00:00<00:00, 269MB/s]
+100%|##########| 170M/170M [00:00<00:00, 250MB/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').
@@ -515,7 +514,7 @@ 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> ( 2 minutes 53.890 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 50.776 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 c5e1c9ef4..951757b88 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -453,7 +453,8 @@ 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, 160MB/s]
+ 63%|######3 | 8.58M/13.6M [00:00<00:00, 89.9MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 108MB/s]
</pre></div>
</div>
</div>
@@ -542,7 +543,7 @@ 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)
- 90.3393 90.2856 91.6459 90.1674 0.2036
+ 90.4142 90.2771 94.9720 90.0825 0.6962
</pre></div>
</div>
<div class="admonition note">
@@ -581,7 +582,7 @@ 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 6.060 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.075 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 b86b4c737..c5bec33e8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -546,7 +546,7 @@ 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)
- 119.6619 119.6320 122.2336 118.9508 0.4077
+ 119.8766 119.8199 123.5409 118.8294 0.5558
</pre></div>
</div>
<div class="admonition note">
@@ -574,7 +574,7 @@ 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 56.349 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 54.807 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 4e16d3e88..e06e6d4fb 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -485,7 +485,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.021 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.893 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 8653d6902..5f2e3f057 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -417,22 +417,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|4 | 5504/132723 [00:00<00:02, 55037.17KB/s]
- 10%|# | 13792/132723 [00:00<00:01, 71409.99KB/s]
- 17%|#6 | 22461/132723 [00:00<00:01, 78381.56KB/s]
- 23%|##3 | 31060/132723 [00:00<00:01, 81381.89KB/s]
- 30%|##9 | 39655/132723 [00:00<00:01, 83027.31KB/s]
- 36%|###6 | 48258/132723 [00:00<00:01, 84046.35KB/s]
- 43%|####2 | 56788/132723 [00:00<00:00, 84454.30KB/s]
- 49%|####9 | 65340/132723 [00:00<00:00, 84790.48KB/s]
- 56%|#####5 | 73913/132723 [00:00<00:00, 85083.06KB/s]
- 62%|######2 | 82515/132723 [00:01<00:00, 85369.49KB/s]
- 69%|######8 | 91091/132723 [00:01<00:00, 85487.03KB/s]
- 75%|#######5 | 99678/132723 [00:01<00:00, 85600.57KB/s]
- 82%|########1 | 108243/132723 [00:01<00:00, 85612.97KB/s]
- 88%|########8 | 116805/132723 [00:01<00:00, 85573.96KB/s]
- 95%|#########4| 125468/132723 [00:01<00:00, 85890.15KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 83685.26KB/s]
+ 5%|5 | 6858/132723 [00:00<00:01, 68571.24KB/s]
+ 11%|#1 | 15209/132723 [00:00<00:01, 77350.19KB/s]
+ 17%|#7 | 22945/132723 [00:00<00:01, 71088.15KB/s]
+ 24%|##3 | 31315/132723 [00:00<00:01, 75813.00KB/s]
+ 29%|##9 | 38955/132723 [00:00<00:01, 72345.12KB/s]
+ 36%|###5 | 47356/132723 [00:00<00:01, 76094.36KB/s]
+ 42%|####1 | 55716/132723 [00:00<00:00, 78455.73KB/s]
+ 48%|####8 | 64105/132723 [00:00<00:00, 80137.45KB/s]
+ 55%|#####4 | 72613/132723 [00:00<00:00, 81653.70KB/s]
+ 61%|######1 | 81031/132723 [00:01<00:00, 82422.56KB/s]
+ 67%|######7 | 89294/132723 [00:01<00:00, 81116.66KB/s]
+ 74%|#######3 | 97666/132723 [00:01<00:00, 81893.67KB/s]
+ 80%|#######9 | 105870/132723 [00:01<00:00, 71576.00KB/s]
+ 86%|########6 | 114331/132723 [00:01<00:00, 75117.84KB/s]
+ 92%|#########2| 122722/132723 [00:01<00:00, 77575.93KB/s]
+ 99%|#########8| 131194/132723 [00:01<00:00, 79614.29KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 77712.82KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -475,7 +476,7 @@ 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 18.289 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 16.315 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 1ae91dedf..76f79e80d 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>10:21.098</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:08.461</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -312,31 +312,31 @@
</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>02:53.890</p></td>
+<td><p>02:50.776</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>02:18.289</p></td>
+<td><p>02:16.315</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:56.349</p></td>
+<td><p>01:54.807</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:16.021</p></td>
+<td><p>01:10.893</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>01:06.060</p></td>
+<td><p>01:06.075</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>00:28.844</p></td>
+<td><p>00:27.963</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>00:21.639</p></td>
+<td><p>00:21.627</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 4f3792caf..22f05849c 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -585,7 +585,7 @@ 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.zip956411ac-acf7-4678-bff3-fb659e097f32 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.zip9cea7fb9-22ce-40b1-aebb-8d0c6c1c78b3 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>
@@ -649,7 +649,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: 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. "
- Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+ Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registered for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index f0b4eabd0..0648a23c8 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>00:39.364</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:38.567</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,19 +312,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:36.217</p></td>
+<td><p>00:35.527</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>00:02.227</p></td>
+<td><p>00:02.137</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>00:00.913</p></td>
+<td><p>00:00.894</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.008</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index c63e09a69..f16a0f122 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -488,10 +488,10 @@ 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: 6975us [6975us] (45.29%; 45.29%)
-FoldScaleAxis: 8426us [7us] (54.71%; 54.71%)
- FoldConstant: 8419us [1732us] (54.66%; 99.91%)
- InferType: 6686us [6686us] (43.42%; 79.42%)
+InferType: 6527us [6527us] (45.71%; 45.71%)
+FoldScaleAxis: 7752us [5us] (54.29%; 54.29%)
+ FoldConstant: 7747us [1569us] (54.25%; 99.93%)
+ InferType: 6178us [6178us] (43.26%; 79.75%)
</pre></div>
</div>
</div>
@@ -513,10 +513,10 @@ 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: 6576us [6576us] (44.80%; 44.80%)
-FoldScaleAxis: 8101us [5us] (55.20%; 55.20%)
- FoldConstant: 8096us [1660us] (55.16%; 99.94%)
- InferType: 6436us [6436us] (43.85%; 79.50%)
+InferType: 6217us [6217us] (44.46%; 44.46%)
+FoldScaleAxis: 7766us [5us] (55.54%; 55.54%)
+ FoldConstant: 7761us [1598us] (55.50%; 99.94%)
+ InferType: 6163us [6163us] (44.07%; 79.41%)
</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 e8a77fc02..d146c7c25 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -537,7 +537,7 @@ 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: 44.969186 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.788746 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 09190bf70..f503d20bf 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -879,7 +879,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.915422 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.080938 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 4bc94e557..f593d2726 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -434,8 +434,8 @@ 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: 0.018415
-Baseline: 3.340516
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018322
+Baseline: 3.286196
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -495,7 +495,7 @@ 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: 0.297967
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.303289
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -562,7 +562,7 @@ 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: 0.334222
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.327262
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -623,7 +623,7 @@ 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: 0.118283
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117826
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -706,7 +706,7 @@ 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: 0.111485
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110779
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -792,7 +792,7 @@ 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: 0.112130
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111495
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -882,7 +882,7 @@ 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: 0.145464
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145484
</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 fd3c67d20..0ec5af7a0 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.155</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.065</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,15 +312,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:31.936</p></td>
+<td><p>00:31.739</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>00:01.230</p></td>
+<td><p>00:01.299</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>00:00.990</p></td>
+<td><p>00:01.027</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 c7734824f..9653d02d3 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>05:10.819</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:23.995</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -312,27 +312,27 @@
</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>02:33.823</p></td>
+<td><p>02:37.630</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>01:19.605</p></td>
+<td><p>01:19.543</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>00:43.015</p></td>
+<td><p>00:42.335</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>00:17.334</p></td>
+<td><p>00:27.898</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:08.557</p></td>
+<td><p>00:08.358</p></td>
<td><p>0.0 MB</p></td>
</tr>
<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>00:08.485</p></td>
+<td><p>00:08.232</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 4169c9531..1a7f4e55d 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
@@ -467,84 +467,599 @@ 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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [252]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [96]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=16)[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, [2016]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1536]), 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
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 128) {
+ 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, 16) {
for (rx.outer.outer: int32, 0, 3) {
- let cse_var_1: int32 = (rc.outer.outer*196)
+ let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_1: int32 = (rc.outer.outer*1568)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [252], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_1 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv(threadIdx.x_1, 7) + 14), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(thr [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else((((floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_1 + (floordiv((floordiv(threadIdx.x_1, 7) + 28), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((7 <= floormod((threadIdx.x_1*4), 63)) && (floormod((threadIdx.x_1*4), 63) < 56)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1*4), 63)*49)) + rx.outer.outer) + floormod((threadIdx.x_1*4), 6 [...]
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*4) + 1), 63)) && (floormod(((threadIdx.x_1*4) + 1), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*4) + 1), 63)*49)) + rx.outer.outer) + floormod(((threadIdx.x_1*4) + 1), 63)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*4) + 2), 63)) && (floormod(((threadIdx.x_1*4) + 2), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*4) + 2), 63)*49)) + rx.outer.outer) + floormod(((threadIdx.x_1*4) + 2), 63)) - 8)], 0f32, dtype=float32)
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((7 <= floormod(((threadIdx.x_1*4) + 3), 63)) && (floormod(((threadIdx.x_1*4) + 3), 63) < 56)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*4) + 3), 63)*49)) + rx.outer.outer) + floormod(((threadIdx.x_1*4) + 3), 63)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1: Buffer(kernel.shared, float32, [96], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + (floordiv(threadIdx.x_2, 12)*4608)) + (rc.outer.outer*36)) + (floormod(threadIdx.x_2, 12)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 32), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 5), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 5), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_ [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 32), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 32), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 32), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 5), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 5), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 64), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 1), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 1), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_ [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 64), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 64), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 64), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 1), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 1), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 1), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 96), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 6), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 6), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse_ [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 96), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadIdx [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 96), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadIdx [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 96), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 6), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 6), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadIdx [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 128), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 2), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 2), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 128), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 128), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 128), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 2), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 2), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 160), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 7), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 7), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 160), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 7), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 7), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 160), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 7), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 7), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 160), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 7), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 7), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 192), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 3), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 3), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 192), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 192), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 192), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 3), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 3), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 224), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 8), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 8), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 224), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 8), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 8), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 224), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 8), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 8), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 224), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 8), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 8), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
+ pad_temp.shared_1[(((floordiv((floordiv((threadIdx.x_1*4), 7) + 256), 9)*63) + (floormod((floordiv((threadIdx.x_1*4), 7) + 4), 9)*7)) + floormod((threadIdx.x_1*4), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 7) + 4), 9)) && (floormod((floordiv((threadIdx.x_1*4), 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod((threadIdx.x_1*4), 7)))) && ((rx.outer.outer + floormod((threadIdx.x_1*4), 7)) < 8)), data[(((((cse [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 1), 7) + 256), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 4), 9)*7)) + floormod(((threadIdx.x_1*4) + 1), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 4), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 1), 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 1), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 2), 7) + 256), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 4), 9)*7)) + floormod(((threadIdx.x_1*4) + 2), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 4), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 2), 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 2), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ pad_temp.shared_1[(((floordiv((floordiv(((threadIdx.x_1*4) + 3), 7) + 256), 9)*63) + (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 4), 9)*7)) + floormod(((threadIdx.x_1*4) + 3), 7))] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 4), 9)) && (floormod((floordiv(((threadIdx.x_1*4) + 3), 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(((threadIdx.x_1*4) + 3), 7)))) && ((rx.outer.outer + floormod(((threadId [...]
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1536], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + cse_var_2) + (threadIdx.x_2*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 7), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 112), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 21), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 224), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 35), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 280), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 42), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 49), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 392), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 63), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 560), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 616)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 77), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 616), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 728)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 91), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 728), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 784), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 840)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 105), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 896), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 952)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 119), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 952), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 126), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1064)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 133), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1064), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1120), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 147), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1232)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 154), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1232), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1288)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 161), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1288), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((blockIdx.x*73728) + cse_var_2) + (floordiv(threadIdx.x_2, 3)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1400)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 175), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1400), 96), 3)*9)) + (floormod((threadIdx.x_2 + 2), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ kernel.shared_1[(threadIdx.x_2 + 1456)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 182), 12)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1456), 96), 3)*9)) + (floormod((threadIdx.x_2 + 1), 3)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
+ if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1512)] = kernel[((((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 189), 12)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 24), 32)*9)) + (floormod(threadIdx.x_2, 3)*3)) + rx.outer.outer)]
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((ry.outer.inner*7) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*192) + ry.outer.inner)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1029)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1036)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1043)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1050)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1092)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1099)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1113)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1232)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1239)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1295)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1302)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1358)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1365)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1421)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1428)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1484)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1533)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1547)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1554)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1596)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1610)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1617)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1659)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1673)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1680)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1722)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1736)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1743)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1785)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1799)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1806)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1848)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1862)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1869)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1911)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1925)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1932)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1974)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1988)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1995)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 93)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((ry.outer.inner*7) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 96)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 99)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 147)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 161)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 168)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 102)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 210)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 224)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 231)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 105)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 273)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 287)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 294)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 108)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 336)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 350)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 357)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 111)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 399)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 413)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 420)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 114)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 462)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 469)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 476)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 483)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 117)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 525)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 532)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 539)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 546)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 120)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 588)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 595)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 602)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 609)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 123)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 651)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 665)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 672)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 126)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 714)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 721)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 728)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 735)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 129)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 777)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 784)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 791)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 798)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 132)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 840)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 847)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 854)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 861)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 135)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 903)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 917)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 924)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 138)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 966)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 980)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 987)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 141)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1029)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1036)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1043)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1050)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 144)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1092)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1099)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1106)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1113)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 147)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1169)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1176)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 150)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1232)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1239)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 153)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1295)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1302)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 156)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1344)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1351)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1358)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1365)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 159)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1407)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1414)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1421)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1428)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 162)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1470)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1477)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1484)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1491)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 165)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1533)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1540)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1547)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1554)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 168)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1596)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1603)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1610)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1617)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 171)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1659)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1666)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1673)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1680)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 174)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1722)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1729)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1736)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1743)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 177)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1785)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1792)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1799)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1806)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 180)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1848)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1855)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1862)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1869)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 183)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1911)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1918)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1925)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1932)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 186)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1974)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1981)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1988)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((ry.outer.inner*7) + floormod(threadIdx.x, 7)) + 1995)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*192) + ry.outer.inner) + 189)]))
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 38)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 39)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 40)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 42)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 43)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 44)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*8) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i2.inner: int32, 0, 7) {
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -581,7 +1096,7 @@ 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: 0.332 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.400 ms
</pre></div>
</div>
</div>
@@ -611,32 +1126,32 @@ 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=4)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_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_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=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=32)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_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)
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=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_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=7)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -659,14 +1174,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+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)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+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", 64)
+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:
@@ -684,78 +1199,550 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[252];
- __shared__ float kernel_shared[96];
+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[2016];
+ __shared__ float kernel_shared[1536];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
+ 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 < 16; ++rc_outer_outer) {
for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 98) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 56) {
- pad_temp_shared[(((int)threadIdx.x) + 196)] = ((((((int)threadIdx.x) < 49) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 196) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 96) {
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) % 12) * 3)) + rx_outer_outer)];
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((7 <= ((((int)threadIdx.x) * 4) % 63)) && (((((int)threadIdx.x) * 4) % 63) < 56)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 63) * 49)) + rx_outer_outer) + ((((int)threadIdx.x) * 4) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((7 <= (((((int)threadIdx.x) * 4) + 1) % 63)) && ((((((int)threadIdx.x) * 4) + 1) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 63) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 4) + 1) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((7 <= (((((int)threadIdx.x) * 4) + 2) % 63)) && ((((((int)threadIdx.x) * 4) + 2) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 63) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 4) + 2) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((7 <= (((((int)threadIdx.x) * 4) + 3) % 63)) && ((((((int)threadIdx.x) * 4) + 3) % 63) < 56)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 3) / 63) * 49)) + rx_outer_outer) + (((((int)threadIdx.x) * 4) + 3) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 224) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 5) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 5) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 225) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 226) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 227) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 5) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 5) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 448) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 1) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 449) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 450) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 451) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 1) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 672) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 6) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 6) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 673) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 674) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 675) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 6) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 6) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 896) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 2) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 897) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 898) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 899) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 2) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 15 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1120) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 7) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1121) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 7) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 7) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1122) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 7) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 7) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1123) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 7) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 7) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1344) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 3) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 3) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1345) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1346) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1347) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 3) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 3) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1568) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 8) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 8) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1569) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 8) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 8) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1570) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 8) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 8) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1571) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 8) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 8) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1792) / 63) * 63) + (((((((int)threadIdx.x) * 4) / 7) + 4) % 9) * 7)) + ((((int)threadIdx.x) * 4) % 7))] = (((((1 <= ((((((int)threadIdx.x) * 4) / 7) + 4) % 9)) && (((((((int)threadIdx.x) * 4) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)))) && ((rx_outer_outer + ((((int)threadIdx.x) * 4) % 7)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1793) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 1) / 7) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) / 7) + 4) % 9)) && ((((((((int)threadIdx.x) * 4) + 1) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 1) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1794) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 2) / 7) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) / 7) + 4) % 9)) && ((((((((int)threadIdx.x) * 4) + 2) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 2) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ pad_temp_shared[((((((((int)threadIdx.x) * 4) + 1795) / 63) * 63) + ((((((((int)threadIdx.x) * 4) + 3) / 7) + 4) % 9) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 7))] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) / 7) + 4) % 9)) && ((((((((int)threadIdx.x) * 4) + 3) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)))) && ((rx_outer_outer + (((((int)threadIdx.x) * 4) + 3) % 7)) < 8)) ? data[((((((rc_outer_outer * 1 [...]
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 168) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 280) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 504) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 8) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 616)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 616) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 40) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 728)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 728) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 840)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 840) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 24) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 952)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 952) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 88) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1008) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1064)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1064) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 64) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 8) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1232)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1232) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 80) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1288)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1288) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 40) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1400)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1400) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 2) % 3) * 3)) + rx_outer_outer)];
+ kernel_shared[(((int)threadIdx.x) + 1456)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1456) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (((((int)threadIdx.x) + 1) % 3) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 24) {
+ kernel_shared[(((int)threadIdx.x) + 1512)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1512) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 24) * 9)) + ((((int)threadIdx.x) % 3) * 3)) + rx_outer_outer)];
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 38)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 40)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 43)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 44)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 48) + 47)]));
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((ry_outer_inner * 7) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((int)threadIdx.x) / 7) * 192) + ry_outer_inner)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1029)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1036)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1043)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1050)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1092)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1099)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1113)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1232)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1239)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1295)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1302)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1358)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1365)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1421)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1428)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1484)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1533)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1547)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1554)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1596)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1610)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1617)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1659)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1673)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1680)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1722)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1736)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1743)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1785)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1799)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1806)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1848)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1862)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1869)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1911)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1925)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1932)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1974)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1988)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1995)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 93)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((ry_outer_inner * 7) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 99)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 147)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 161)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 168)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 102)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 210)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 224)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 231)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 105)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 273)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 287)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 294)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 108)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 336)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 350)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 357)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 111)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 399)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 413)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 420)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 114)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 462)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 469)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 476)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 483)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 117)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 525)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 532)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 539)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 546)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 120)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 588)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 595)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 602)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 609)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 123)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 651)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 665)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 672)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 126)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 714)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 721)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 728)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 735)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 129)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 777)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 784)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 791)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 798)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 132)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 840)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 847)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 854)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 861)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 135)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 903)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 917)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 924)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 138)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 966)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 980)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 987)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 141)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1029)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1036)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1043)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1050)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 144)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1092)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1099)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1106)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1113)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 147)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1169)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1176)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 150)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1232)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1239)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 153)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1295)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1302)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 156)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1344)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1351)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1358)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1365)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 159)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1407)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1414)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1421)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1428)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 162)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1470)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1477)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1484)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1491)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 165)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1533)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1540)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1547)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1554)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 168)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1596)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1603)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1610)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1617)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 171)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1659)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1666)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1673)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1680)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 174)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1722)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1729)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1736)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1743)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 177)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1785)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1792)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1799)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1806)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 180)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1848)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1855)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1862)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1869)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 183)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1911)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1918)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1925)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1932)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 186)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1974)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1981)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1988)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((ry_outer_inner * 7) + (((int)threadIdx.x) % 7)) + 1995)] * kernel_shared[((((((int)threadIdx.x) / 7) * 192) + ry_outer_inner) + 189)]));
+ }
}
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 8) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -792,7 +1779,7 @@ 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 33.823 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 37.630 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 0f8acd709..aed61eea4 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -882,7 +882,7 @@ 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)
- 10.1713 10.1826 10.1906 10.1407 0.0219
+ 9.5812 9.5758 9.6298 9.5379 0.0377
</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 e77d427fa..77f93a1c6 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.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)
- 759.3360 761.0120 761.4977 755.4984 2.7209
+ 762.0268 762.2833 763.4970 760.3000 1.3177
</pre></div>
</div>
</div>
@@ -923,7 +923,7 @@ 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 19.605 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.543 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 26e2538fc..dc0d05cb1 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -601,29 +601,81 @@ 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_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 32) {
- for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [2048], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ for (i0.outer: int32, 0, 4) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 4) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- for (i.inner: int32, 0, 4) {
- for (j: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner*16)) + j)
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 8) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i0.outer*8192) + (i.outer.inner*2048)) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_2: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*16))
- compute[ramp(cse_var_2, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_2, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_22: int32 = ((((i0.outer*16384) + (i0.inner*512)) + (i1.outer*32)) + i1.inner)
+ compute[cse_var_22] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
+ }
}
}
}
@@ -661,7 +713,7 @@ 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: 1.455 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.819 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 04d9762fe..f03db0e32 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>00:42.689</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:42.951</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,7 +312,7 @@
</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>00:42.660</p></td>
+<td><p>00:42.922</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>
@@ -324,7 +324,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
-<td><p>00:00.005</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>
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 109fcffb1..ba8c532b4 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1145,8 +1145,8 @@ 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: 92.75/92.75 result: MeasureResult(costs=(0.002496006854166667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6259727478027344, timestamp=1655499340.9969175) [('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: 0.00/92.75 result: Traceback (most recent call last):
+No: 6 GFLOPS: 104.14/104.14 result: MeasureResult(costs=(0.0022229111875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6228270530700684, timestamp=1655547517.125957) [('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: 0.00/104.14 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
@@ -1269,7 +1269,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/104.14 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
@@ -1392,7 +1392,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/104.14 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
@@ -1515,7 +1515,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/104.14 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
@@ -1533,7 +1533,7 @@ No: 10 GFLOPS: 0.00/92.75 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/104.14 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
@@ -1656,7 +1656,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/104.14 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
@@ -1779,7 +1779,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/104.14 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
@@ -1902,7 +1902,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/104.14 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
@@ -2025,7 +2025,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/104.14 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
@@ -2148,7 +2148,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/104.14 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
@@ -2271,7 +2271,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/104.14 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
@@ -2394,7 +2394,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/104.14 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
@@ -2517,7 +2517,7 @@ 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: 0.00/92.75 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/104.14 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
@@ -2605,7 +2605,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f978e86bfa2
+ 12: 0x00007fabe7284fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2670,7 +2670,7 @@ 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: 141.96/141.96 result: MeasureResult(costs=(0.001630721612903226,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.14066743850708, timestamp=1655499367.1597893) [('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: 144.08/144.08 result: MeasureResult(costs=(0.0016067480317460317,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1308460235595703, timestamp=1655547543.3468952) [('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,
@@ -2711,7 +2711,7 @@ 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: 0.001979
+Time cost of this operator: 0.002044
</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 e73348f11..e635828c8 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -559,10 +559,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 320.1 98.77 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.948 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.914 0.282 (1, 1, 10, 10, 3) 1 1
-Total_time - 324.086 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 316.9 98.747 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.097 0.965 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.925 0.288 (1, 1, 10, 10, 3) 1 1
+Total_time - 320.922 - - - -
</pre></div>
</div>
</div>
@@ -615,10 +615,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 96.05 97.255 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.876 1.899 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.835 0.845 (1, 3, 10, 10, 1) 1 1
-Total_time - 98.761 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 153.3 98.271 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.775 1.138 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 0.59 (1, 1, 10, 10, 3) 1 1
+Total_time - 155.997 - - - -
</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 de406dd84..4d1628a7c 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -490,7 +490,7 @@ 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/tmpgba5o3yp/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpflj5o_4o/images/random'
</pre></div>
</div>
</div>
@@ -550,8 +550,8 @@ 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/tmpgba5o3yp/images/target contains 8144 images
-/tmp/tmpgba5o3yp/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/tmpflj5o_4o/images/target contains 8144 images
+/tmp/tmpflj5o_4o/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -663,13 +663,13 @@ 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 - 55s - loss: 0.2192 - accuracy: 0.9256 - val_loss: 0.1453 - val_accuracy: 0.9543
+328/328 - 54s - loss: 0.2134 - accuracy: 0.9271 - val_loss: 0.1380 - val_accuracy: 0.9585
Epoch 2/3
-328/328 - 52s - loss: 0.1007 - accuracy: 0.9627 - val_loss: 0.1348 - val_accuracy: 0.9573
+328/328 - 52s - loss: 0.0972 - accuracy: 0.9639 - val_loss: 0.1234 - val_accuracy: 0.9607
Epoch 3/3
-328/328 - 52s - loss: 0.0641 - accuracy: 0.9764 - val_loss: 0.1642 - val_accuracy: 0.9441
+328/328 - 52s - loss: 0.0673 - accuracy: 0.9752 - val_loss: 0.1572 - val_accuracy: 0.9479
-<keras.callbacks.History object at 0x7facc58f1210>
+<keras.callbacks.History object at 0x7ff1e86f54d0>
</pre></div>
</div>
</div>
@@ -931,7 +931,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 41.868 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 8.713 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 59fd0fe99..d7f2a3f77 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>05:27.030</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>04:53.897</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,22 +312,22 @@
</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>04:41.868</p></td>
+<td><p>04:08.713</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>00:41.680</p></td>
+<td><p>00:41.732</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>00:03.482</p></td>
+<td><p>00:03.451</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>
+<tr class="row-even"><td><p><a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 2d7b7278f..2cf7ff9af 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>00:11.440</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:11.773</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,11 +312,11 @@
</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>00:09.932</p></td>
+<td><p>00:09.981</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>00:01.502</p></td>
+<td><p>00:01.786</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 3d8716b4a..ab92fc3a9 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -496,7 +496,7 @@ 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 0x7fac4475ea70>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7ff159c1d200>
</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 66414ff5d..32250df6a 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>00:03.958</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.189</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,31 +312,31 @@
</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>00:01.858</p></td>
+<td><p>00:01.930</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>00:00.922</p></td>
+<td><p>00:01.028</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>00:00.512</p></td>
+<td><p>00:00.539</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>00:00.498</p></td>
+<td><p>00:00.520</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>00:00.098</p></td>
+<td><p>00:00.099</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>00:00.032</p></td>
+<td><p>00:00.033</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>00:00.028</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 deb418c9c..2dc5265ce 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -552,7 +552,7 @@ 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/tmpo8sjud83/input0.cc'\nsource_filename = \"/tmp/tmpo8sjud83/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/tmpc4amql8y/input0.cc'\nsource_filename = \"/tmp/tmpc4amql8y/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 b6a48d8a6..68a897914 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1718,7 +1718,7 @@ Can be the a function or the function name.</p></li>
<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">
@@ -1755,7 +1755,7 @@ the initial naive schedule (state).</p>
<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>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index e95f32fdc..3ec1e1d2c 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/2708b6ca0/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 14ae65f11..ea20dd9b0 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/2708b6ca0/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 536d68f30..c999515e8 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/2708b6ca0/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 95efefe7e..73d7de571 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/2708b6ca0/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 f99bc5c04..eac0f9018 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/2708b6ca0/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 093fbb7e2..05ff54bce 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/2708b6ca0/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 bbc2d06f3..1c9a94963 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/2708b6ca0/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 ed78d848e..8f9e3ecaf 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/2708b6ca0/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/web/src/runtime.ts#L1134">runtime.ts:1134</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/2708b6ca0/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 8e0d2eab5..175c72064 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/2708b6ca0/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 5dfa443b7..eb7fc1202 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/2708b6ca0/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 bdd6cc21f..96bf1f9c1 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/2708b6ca0/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 d713c6e82..58a3e218f 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/2708b6ca0/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 180ace06f..4d58cacbb 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/2708b6ca0/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 ef8c233a7..1237f38f9 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/2708b6ca0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 425b1261c..f1a627397 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/2708b6ca0/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 f903e799b..4e755cb9b 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/2708b6ca0/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 3b8bf421e..f5d9f3fcd 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/2708b6ca0/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 b9851de0d..ba429d5c4 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/2708b6ca0/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 8f2e36fa2..6e15e04f7 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/2708b6ca0/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 ce18a4f42..6cb925312 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/2708b6ca0/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 8dcda1563..7afd02d1a 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/2708b6ca0/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/web/src/runtime.ts#L1356">runtime.ts:1356</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/2708b6ca0/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 1244153a4..e134aa4ae 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/2708b6ca0/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 a981210b6..b30ede7d0 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/2708b6ca0/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 0e022dd83..c15170e18 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/2708b6ca0/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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/2708b6ca0/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f8b320f52/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 2a7872672..b8ceb8edd 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 343f17187..8d49d66d5 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>00:21.456</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.190</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -312,7 +312,7 @@
</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>00:21.450</p></td>
+<td><p>00:20.184</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 395f10839..78e32f129 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -547,7 +547,7 @@ 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 21.92s!
+resnet18_v1 inference graph built in 21.90s!
</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 bf1984992..cf49d2079 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -565,7 +565,7 @@ 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:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.52s!
+yolov3-tiny inference graph built in 15.22s!
</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 651a4cc5d..31fcee5e3 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>01:29.609</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:29.517</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</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>00:47.590</p></td>
+<td><p>00:47.240</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>00:42.019</p></td>
+<td><p>00:42.277</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 d4e1432b0..7d7397d9a 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>00:03.206</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.253</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</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>00:02.825</p></td>
+<td><p>00:02.845</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>00:00.381</p></td>
+<td><p>00:00.408</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 7c8c893aa..3257c3b86 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>00:00.663</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.713</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -312,11 +312,11 @@
</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>00:00.342</p></td>
+<td><p>00:00.363</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>00:00.321</p></td>
+<td><p>00:00.350</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 31b0ed793..1ba9f4ba8 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -542,7 +542,7 @@ 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: 93.982 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.128 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 87a9eada1..e216fd30a 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -641,16 +641,16 @@ 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: 9.35/9.35 result: MeasureResult(costs=(0.028716855399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5912308692932129, timestamp=1655498227.4835176) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.70/9.35 result: MeasureResult(costs=(0.0993026256,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.737971544265747, timestamp=1655498229.7333903) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.0228017096,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6217353343963623, timestamp=1655498230.308111) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.59/11.77 result: MeasureResult(costs=(0.16856198579999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8178319931030273, timestamp=1655498233.662976) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.62/11.77 result: MeasureResult(costs=(0.0740766746,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.31612229347229, timestamp=1655498235.1075253) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.79/11.77 result: MeasureResult(costs=(0.150043006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5395121574401855, timestamp=1655498238.1772516) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/11.77 result: MeasureResult(costs=(0.3078512572,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.041301965713501, timestamp=1655498243.266006) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.67/11.77 result: MeasureResult(costs=(0.0251541648,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5451865196228027, timestamp=1655498243.832165) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.90/11.77 result: MeasureResult(costs=(0.1411295772,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3584036827087402, timestamp=1655498246.3086474) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.78/11.77 result: MeasureResult(costs=(0.0966992672,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6482198238372803, timestamp=1655498248.016553) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.57/9.57 result: MeasureResult(costs=(0.028064028400000003,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5799887180328369, timestamp=1655546421.4435875) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.72/9.57 result: MeasureResult(costs=(0.0988507958,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7334237098693848, timestamp=1655546423.687424) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.83/11.83 result: MeasureResult(costs=(0.022698381,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5857813358306885, timestamp=1655546424.2558951) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.74/11.83 result: MeasureResult(costs=(0.1539023714,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5779600143432617, timestamp=1655546427.3689713) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.64/11.83 result: MeasureResult(costs=(0.0737395022,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3057539463043213, timestamp=1655546428.8032825) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.67/11.83 result: MeasureResult(costs=(0.1606874056,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.721618890762329, timestamp=1655546431.5740023) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.83 result: MeasureResult(costs=(0.3085565634,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.055051803588867, timestamp=1655546437.1731834) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.42/11.83 result: MeasureResult(costs=(0.025761548599999996,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5520608425140381, timestamp=1655546437.7473106) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.60/11.83 result: MeasureResult(costs=(0.1677022536,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7814273834228516, timestamp=1655546440.647709) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.79/11.83 result: MeasureResult(costs=(0.0962706418,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6412205696105957, timestamp=1655546442.3491547) [('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 f12abd2f3..301ee0b70 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -523,7 +523,7 @@ 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': 492.91474093000033, 'median': 491.8427488500015, 'std': 2.815318947956547}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 493.1380477699986, 'median': 492.5971845999811, 'std': 1.245634467347975}
</pre></div>
</div>
</div>
@@ -678,179 +678,179 @@ 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: 17.57/ 17.57 GFLOPS | Progress: (4/20) | 6.00 s
-[Task 1/25] Current/Best: 6.16/ 17.57 GFLOPS | Progress: (8/20) | 8.95 s
-[Task 1/25] Current/Best: 11.56/ 22.71 GFLOPS | Progress: (12/20) | 11.35 s
-[Task 1/25] Current/Best: 16.79/ 22.80 GFLOPS | Progress: (16/20) | 13.02 s
-[Task 1/25] Current/Best: 11.61/ 23.52 GFLOPS | Progress: (20/20) | 14.75 s Done.
+[Task 1/25] Current/Best: 17.56/ 17.56 GFLOPS | Progress: (4/20) | 5.59 s
+[Task 1/25] Current/Best: 6.16/ 17.56 GFLOPS | Progress: (8/20) | 8.94 s
+[Task 1/25] Current/Best: 11.55/ 22.83 GFLOPS | Progress: (12/20) | 11.35 s
+[Task 1/25] Current/Best: 16.77/ 22.83 GFLOPS | Progress: (16/20) | 13.02 s
+[Task 1/25] Current/Best: 11.65/ 23.92 GFLOPS | Progress: (20/20) | 14.75 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.31/ 12.96 GFLOPS | Progress: (4/20) | 3.73 s
-[Task 2/25] Current/Best: 13.84/ 18.62 GFLOPS | Progress: (8/20) | 5.01 s
-[Task 2/25] Current/Best: 20.96/ 20.96 GFLOPS | Progress: (12/20) | 6.36 s
-[Task 2/25] Current/Best: 11.79/ 20.96 GFLOPS | Progress: (16/20) | 7.62 s
-[Task 2/25] Current/Best: 19.98/ 20.96 GFLOPS | Progress: (20/20) | 9.16 s Done.
+[Task 2/25] Current/Best: 12.34/ 13.01 GFLOPS | Progress: (4/20) | 3.72 s
+[Task 2/25] Current/Best: 14.15/ 18.09 GFLOPS | Progress: (8/20) | 5.01 s
+[Task 2/25] Current/Best: 21.29/ 21.29 GFLOPS | Progress: (12/20) | 6.32 s
+[Task 2/25] Current/Best: 12.53/ 21.29 GFLOPS | Progress: (16/20) | 7.60 s
+[Task 2/25] Current/Best: 18.96/ 21.29 GFLOPS | Progress: (20/20) | 9.17 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/ 10.54 GFLOPS | Progress: (4/20) | 5.80 s
-[Task 3/25] Current/Best: 15.57/ 16.84 GFLOPS | Progress: (8/20) | 7.73 s
-[Task 3/25] Current/Best: 14.87/ 16.84 GFLOPS | Progress: (12/20) | 9.44 s
-[Task 3/25] Current/Best: 7.18/ 23.72 GFLOPS | Progress: (16/20) | 11.34 s
-[Task 3/25] Current/Best: 12.59/ 23.72 GFLOPS | Progress: (20/20) | 15.86 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.56 GFLOPS | Progress: (4/20) | 5.82 s
+[Task 3/25] Current/Best: 15.60/ 16.94 GFLOPS | Progress: (8/20) | 7.72 s
+[Task 3/25] Current/Best: 14.89/ 16.94 GFLOPS | Progress: (12/20) | 9.42 s
+[Task 3/25] Current/Best: 7.19/ 23.82 GFLOPS | Progress: (16/20) | 11.31 s
+[Task 3/25] Current/Best: 11.23/ 23.82 GFLOPS | Progress: (20/20) | 15.85 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.27/ 19.52 GFLOPS | Progress: (4/20) | 2.36 s
-[Task 4/25] Current/Best: 6.86/ 19.52 GFLOPS | Progress: (8/20) | 6.66 s
-[Task 4/25] Current/Best: 21.62/ 21.62 GFLOPS | Progress: (12/20) | 11.17 s
-[Task 4/25] Current/Best: 17.14/ 21.62 GFLOPS | Progress: (16/20) | 13.37 s
-[Task 4/25] Current/Best: 12.69/ 21.62 GFLOPS | Progress: (20/20) | 15.34 s Done.
+[Task 4/25] Current/Best: 9.48/ 20.42 GFLOPS | Progress: (4/20) | 2.31 s
+[Task 4/25] Current/Best: 6.39/ 20.42 GFLOPS | Progress: (8/20) | 6.58 s
+[Task 4/25] Current/Best: 21.73/ 21.73 GFLOPS | Progress: (12/20) | 11.11 s
+[Task 4/25] Current/Best: 16.74/ 21.73 GFLOPS | Progress: (16/20) | 13.31 s
+[Task 4/25] Current/Best: 13.41/ 21.73 GFLOPS | Progress: (20/20) | 15.32 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.67/ 10.36 GFLOPS | Progress: (4/20) | 2.53 s
-[Task 5/25] Current/Best: 11.87/ 12.78 GFLOPS | Progress: (8/20) | 4.59 s
-[Task 5/25] Current/Best: 11.83/ 18.01 GFLOPS | Progress: (12/20) | 7.64 s
-[Task 5/25] Current/Best: 11.77/ 22.66 GFLOPS | Progress: (16/20) | 9.04 s
-[Task 5/25] Current/Best: 12.09/ 22.66 GFLOPS | Progress: (20/20) | 10.88 s Done.
+[Task 5/25] Current/Best: 9.56/ 10.32 GFLOPS | Progress: (4/20) | 2.57 s
+[Task 5/25] Current/Best: 11.65/ 12.73 GFLOPS | Progress: (8/20) | 4.63 s
+[Task 5/25] Current/Best: 11.75/ 17.87 GFLOPS | Progress: (12/20) | 7.53 s
+[Task 5/25] Current/Best: 11.86/ 22.72 GFLOPS | Progress: (16/20) | 8.93 s
+[Task 5/25] Current/Best: 12.05/ 22.72 GFLOPS | Progress: (20/20) | 10.78 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.15/ 20.65 GFLOPS | Progress: (4/20) | 3.86 s
-[Task 6/25] Current/Best: 19.01/ 20.65 GFLOPS | Progress: (8/20) | 5.62 s
-[Task 6/25] Current/Best: 13.29/ 20.65 GFLOPS | Progress: (12/20) | 7.53 s
-[Task 6/25] Current/Best: 20.02/ 20.65 GFLOPS | Progress: (16/20) | 9.80 s
-[Task 6/25] Current/Best: 3.74/ 20.65 GFLOPS | Progress: (20/20) | 12.34 s Done.
+[Task 6/25] Current/Best: 12.16/ 20.80 GFLOPS | Progress: (4/20) | 3.88 s
+[Task 6/25] Current/Best: 19.05/ 20.80 GFLOPS | Progress: (8/20) | 5.63 s
+[Task 6/25] Current/Best: 13.25/ 20.80 GFLOPS | Progress: (12/20) | 7.56 s
+[Task 6/25] Current/Best: 20.04/ 20.80 GFLOPS | Progress: (16/20) | 9.78 s
+[Task 6/25] Current/Best: 3.72/ 20.80 GFLOPS | Progress: (20/20) | 12.28 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.24/ 12.85 GFLOPS | Progress: (4/20) | 3.53 s
-[Task 7/25] Current/Best: 20.31/ 21.16 GFLOPS | Progress: (8/20) | 5.04 s
-[Task 7/25] Current/Best: 16.13/ 21.16 GFLOPS | Progress: (12/20) | 6.96 s
-[Task 7/25] Current/Best: 12.22/ 21.16 GFLOPS | Progress: (16/20) | 8.99 s
-[Task 7/25] Current/Best: 6.36/ 21.62 GFLOPS | Progress: (20/20) | 11.44 s Done.
+[Task 7/25] Current/Best: 11.23/ 12.93 GFLOPS | Progress: (4/20) | 3.52 s
+[Task 7/25] Current/Best: 20.25/ 21.18 GFLOPS | Progress: (8/20) | 5.02 s
+[Task 7/25] Current/Best: 15.94/ 21.18 GFLOPS | Progress: (12/20) | 6.90 s
+[Task 7/25] Current/Best: 12.25/ 21.18 GFLOPS | Progress: (16/20) | 8.92 s
+[Task 7/25] Current/Best: 6.30/ 21.82 GFLOPS | Progress: (20/20) | 11.36 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/ 14.34 GFLOPS | Progress: (4/20) | 2.83 s
-[Task 8/25] Current/Best: 10.11/ 14.34 GFLOPS | Progress: (8/20) | 7.56 s
-[Task 8/25] Current/Best: 12.69/ 14.34 GFLOPS | Progress: (12/20) | 13.63 s
-[Task 8/25] Current/Best: 18.72/ 18.72 GFLOPS | Progress: (16/20) | 15.73 s
-[Task 8/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (20/20) | 22.25 s Done.
+[Task 8/25] Current/Best: 9.97/ 14.24 GFLOPS | Progress: (4/20) | 2.85 s
+[Task 8/25] Current/Best: 9.43/ 14.24 GFLOPS | Progress: (8/20) | 7.59 s
+[Task 8/25] Current/Best: 12.74/ 14.24 GFLOPS | Progress: (12/20) | 13.69 s
+[Task 8/25] Current/Best: 18.91/ 18.91 GFLOPS | Progress: (16/20) | 15.76 s
+[Task 8/25] Current/Best: 19.90/ 19.90 GFLOPS | Progress: (20/20) | 22.20 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.28/ 15.72 GFLOPS | Progress: (4/20) | 11.89 s
-[Task 9/25] Current/Best: 23.04/ 23.04 GFLOPS | Progress: (8/20) | 13.72 s
-[Task 9/25] Current/Best: 8.30/ 23.04 GFLOPS | Progress: (12/20) | 16.05 s
-[Task 9/25] Current/Best: 18.07/ 23.04 GFLOPS | Progress: (16/20) | 18.69 s
-[Task 9/25] Current/Best: 9.05/ 23.04 GFLOPS | Progress: (20/20) | 26.32 s
+[Task 9/25] Current/Best: 14.36/ 14.36 GFLOPS | Progress: (4/20) | 11.91 s
+[Task 9/25] Current/Best: 23.56/ 23.56 GFLOPS | Progress: (8/20) | 13.67 s
+[Task 9/25] Current/Best: 8.27/ 23.56 GFLOPS | Progress: (12/20) | 16.02 s
+[Task 9/25] Current/Best: 17.83/ 23.56 GFLOPS | Progress: (16/20) | 18.55 s
+[Task 9/25] Current/Best: 9.08/ 23.56 GFLOPS | Progress: (20/20) | 26.10 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (4/20) | 2.50 s
-[Task 10/25] Current/Best: 15.44/ 18.23 GFLOPS | Progress: (8/20) | 4.08 s
-[Task 10/25] Current/Best: 12.60/ 19.03 GFLOPS | Progress: (12/20) | 5.59 s
-[Task 10/25] Current/Best: 19.19/ 20.19 GFLOPS | Progress: (16/20) | 6.69 s
-[Task 10/25] Current/Best: 8.86/ 20.19 GFLOPS | Progress: (20/20) | 8.21 s Done.
+[Task 10/25] Current/Best: 18.22/ 18.22 GFLOPS | Progress: (4/20) | 2.48 s
+[Task 10/25] Current/Best: 15.54/ 18.22 GFLOPS | Progress: (8/20) | 4.04 s
+[Task 10/25] Current/Best: 11.81/ 18.95 GFLOPS | Progress: (12/20) | 5.57 s
+[Task 10/25] Current/Best: 19.11/ 20.35 GFLOPS | Progress: (16/20) | 6.66 s
+[Task 10/25] Current/Best: 8.82/ 20.35 GFLOPS | Progress: (20/20) | 8.18 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 11.36/ 18.11 GFLOPS | Progress: (4/20) | 3.27 s
-[Task 11/25] Current/Best: 15.39/ 18.11 GFLOPS | Progress: (8/20) | 6.01 s
-[Task 11/25] Current/Best: 17.83/ 18.11 GFLOPS | Progress: (12/20) | 8.06 s
-[Task 11/25] Current/Best: 13.39/ 21.18 GFLOPS | Progress: (16/20) | 10.83 s
-[Task 11/25] Current/Best: 19.47/ 21.57 GFLOPS | Progress: (20/20) | 12.85 s Done.
+[Task 11/25] Current/Best: 12.24/ 18.12 GFLOPS | Progress: (4/20) | 3.26 s
+[Task 11/25] Current/Best: 16.74/ 18.12 GFLOPS | Progress: (8/20) | 5.99 s
+[Task 11/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (12/20) | 8.03 s
+[Task 11/25] Current/Best: 13.48/ 21.18 GFLOPS | Progress: (16/20) | 10.77 s
+[Task 11/25] Current/Best: 19.51/ 21.51 GFLOPS | Progress: (20/20) | 12.78 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.84/ 18.08 GFLOPS | Progress: (4/20) | 5.27 s
-[Task 12/25] Current/Best: 5.27/ 18.08 GFLOPS | Progress: (8/20) | 8.92 s
-[Task 12/25] Current/Best: 18.95/ 18.95 GFLOPS | Progress: (12/20) | 10.90 s
-[Task 12/25] Current/Best: 15.37/ 18.95 GFLOPS | Progress: (16/20) | 13.63 s
-[Task 12/25] Current/Best: 15.10/ 18.95 GFLOPS | Progress: (20/20) | 15.55 s Done.
+[Task 12/25] Current/Best: 7.81/ 17.96 GFLOPS | Progress: (4/20) | 5.21 s
+[Task 12/25] Current/Best: 5.27/ 17.96 GFLOPS | Progress: (8/20) | 8.83 s
+[Task 12/25] Current/Best: 18.52/ 18.75 GFLOPS | Progress: (12/20) | 10.81 s
+[Task 12/25] Current/Best: 15.34/ 18.75 GFLOPS | Progress: (16/20) | 13.57 s
+[Task 12/25] Current/Best: 15.17/ 18.75 GFLOPS | Progress: (20/20) | 15.52 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.66/ 17.27 GFLOPS | Progress: (4/20) | 3.57 s
-[Task 13/25] Current/Best: 16.12/ 21.08 GFLOPS | Progress: (8/20) | 5.97 s
-[Task 13/25] Current/Best: 19.64/ 21.37 GFLOPS | Progress: (12/20) | 8.88 s
-[Task 13/25] Current/Best: 12.24/ 21.37 GFLOPS | Progress: (16/20) | 12.27 s
-[Task 13/25] Current/Best: 18.76/ 21.37 GFLOPS | Progress: (20/20) | 14.53 s Done.
+[Task 13/25] Current/Best: 8.74/ 17.34 GFLOPS | Progress: (4/20) | 3.56 s
+[Task 13/25] Current/Best: 15.92/ 21.04 GFLOPS | Progress: (8/20) | 5.98 s
+[Task 13/25] Current/Best: 19.76/ 21.83 GFLOPS | Progress: (12/20) | 8.83 s
+[Task 13/25] Current/Best: 12.28/ 21.83 GFLOPS | Progress: (16/20) | 12.21 s
+[Task 13/25] Current/Best: 18.67/ 21.83 GFLOPS | Progress: (20/20) | 14.48 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) | 3.25 s
-[Task 14/25] Current/Best: 6.02/ 13.57 GFLOPS | Progress: (8/20) | 5.41 s
-[Task 14/25] Current/Best: 21.19/ 21.19 GFLOPS | Progress: (12/20) | 7.95 s
-[Task 14/25] Current/Best: 16.21/ 21.19 GFLOPS | Progress: (16/20) | 9.63 s Done.
+[Task 14/25] Current/Best: 13.73/ 13.73 GFLOPS | Progress: (4/20) | 3.24 s
+[Task 14/25] Current/Best: 6.10/ 13.73 GFLOPS | Progress: (8/20) | 5.42 s
+[Task 14/25] Current/Best: 20.29/ 20.29 GFLOPS | Progress: (12/20) | 7.96 s
+[Task 14/25] Current/Best: 16.82/ 20.29 GFLOPS | Progress: (16/20) | 9.63 s Done.
-[Task 14/25] Current/Best: 17.12/ 21.19 GFLOPS | Progress: (20/20) | 11.34 s
+[Task 14/25] Current/Best: 17.23/ 20.29 GFLOPS | Progress: (20/20) | 11.34 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.13/ 17.63 GFLOPS | Progress: (4/20) | 2.61 s
-[Task 15/25] Current/Best: 14.50/ 18.06 GFLOPS | Progress: (8/20) | 3.89 s
-[Task 15/25] Current/Best: 10.38/ 22.31 GFLOPS | Progress: (12/20) | 5.91 s
-[Task 15/25] Current/Best: 20.42/ 22.31 GFLOPS | Progress: (16/20) | 8.90 s
-[Task 15/25] Current/Best: 9.69/ 22.31 GFLOPS | Progress: (20/20) | 9.91 s
+[Task 15/25] Current/Best: 16.18/ 17.69 GFLOPS | Progress: (4/20) | 2.65 s
+[Task 15/25] Current/Best: 13.12/ 18.06 GFLOPS | Progress: (8/20) | 3.94 s
+[Task 15/25] Current/Best: 10.37/ 22.28 GFLOPS | Progress: (12/20) | 5.99 s
+[Task 15/25] Current/Best: 20.28/ 22.28 GFLOPS | Progress: (16/20) | 9.42 s
+[Task 15/25] Current/Best: 9.66/ 22.28 GFLOPS | Progress: (20/20) | 10.43 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.52/ 20.52 GFLOPS | Progress: (4/20) | 2.86 s
-[Task 16/25] Current/Best: 3.04/ 20.52 GFLOPS | Progress: (8/20) | 4.48 s
-[Task 16/25] Current/Best: 19.84/ 20.52 GFLOPS | Progress: (12/20) | 5.69 s
-[Task 16/25] Current/Best: 17.84/ 20.52 GFLOPS | Progress: (16/20) | 7.02 s
-[Task 16/25] Current/Best: 10.06/ 22.33 GFLOPS | Progress: (20/20) | 9.06 s Done.
+[Task 16/25] Current/Best: 20.60/ 20.60 GFLOPS | Progress: (4/20) | 2.94 s
+[Task 16/25] Current/Best: 3.04/ 20.60 GFLOPS | Progress: (8/20) | 4.54 s
+[Task 16/25] Current/Best: 19.41/ 20.60 GFLOPS | Progress: (12/20) | 5.75 s
+[Task 16/25] Current/Best: 17.46/ 20.60 GFLOPS | Progress: (16/20) | 7.07 s
+[Task 16/25] Current/Best: 10.14/ 22.34 GFLOPS | Progress: (20/20) | 9.10 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 11.83/ 18.87 GFLOPS | Progress: (4/20) | 4.70 s
-[Task 17/25] Current/Best: 14.38/ 23.09 GFLOPS | Progress: (8/20) | 7.57 s
-[Task 17/25] Current/Best: 16.92/ 23.09 GFLOPS | Progress: (12/20) | 9.61 s
-[Task 17/25] Current/Best: 16.50/ 23.09 GFLOPS | Progress: (16/20) | 11.72 s
-[Task 17/25] Current/Best: 10.04/ 23.09 GFLOPS | Progress: (20/20) | 13.82 s Done.
+[Task 17/25] Current/Best: 13.18/ 18.85 GFLOPS | Progress: (4/20) | 4.68 s
+[Task 17/25] Current/Best: 14.37/ 23.33 GFLOPS | Progress: (8/20) | 7.41 s
+[Task 17/25] Current/Best: 17.21/ 23.33 GFLOPS | Progress: (12/20) | 9.46 s
+[Task 17/25] Current/Best: 16.52/ 23.33 GFLOPS | Progress: (16/20) | 11.57 s
+[Task 17/25] Current/Best: 10.04/ 23.33 GFLOPS | Progress: (20/20) | 13.68 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.42/ 17.81 GFLOPS | Progress: (4/20) | 3.60 s
-[Task 18/25] Current/Best: 10.59/ 20.06 GFLOPS | Progress: (8/20) | 7.04 s
-[Task 18/25] Current/Best: 19.43/ 20.06 GFLOPS | Progress: (12/20) | 8.98 s
-[Task 18/25] Current/Best: 9.96/ 20.06 GFLOPS | Progress: (16/20) | 12.55 s
-[Task 18/25] Current/Best: 20.64/ 20.64 GFLOPS | Progress: (20/20) | 14.07 s Done.
+[Task 18/25] Current/Best: 11.30/ 17.35 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 18/25] Current/Best: 10.54/ 18.91 GFLOPS | Progress: (8/20) | 7.05 s
+[Task 18/25] Current/Best: 18.58/ 18.91 GFLOPS | Progress: (12/20) | 8.99 s
+[Task 18/25] Current/Best: 10.10/ 18.91 GFLOPS | Progress: (16/20) | 12.50 s
+[Task 18/25] Current/Best: 20.48/ 20.48 GFLOPS | Progress: (20/20) | 14.00 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.03/ 20.31 GFLOPS | Progress: (4/20) | 5.97 s
-[Task 19/25] Current/Best: 2.60/ 20.31 GFLOPS | Progress: (8/20) | 9.25 s
-[Task 19/25] Current/Best: 19.48/ 20.88 GFLOPS | Progress: (12/20) | 12.02 s
-[Task 19/25] Current/Best: 15.36/ 21.38 GFLOPS | Progress: (16/20) | 14.85 s
-[Task 19/25] Current/Best: 2.70/ 23.08 GFLOPS | Progress: (20/20) | 17.62 s Done.
+[Task 19/25] Current/Best: 7.17/ 20.45 GFLOPS | Progress: (4/20) | 5.91 s
+[Task 19/25] Current/Best: 2.61/ 20.45 GFLOPS | Progress: (8/20) | 9.16 s
+[Task 19/25] Current/Best: 18.67/ 21.88 GFLOPS | Progress: (12/20) | 11.97 s
+[Task 19/25] Current/Best: 13.49/ 21.98 GFLOPS | Progress: (16/20) | 14.81 s
+[Task 19/25] Current/Best: 2.70/ 23.64 GFLOPS | Progress: (20/20) | 17.62 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.98/ 15.07 GFLOPS | Progress: (4/20) | 3.27 s Done.
+[Task 20/25] Current/Best: 9.27/ 15.38 GFLOPS | Progress: (4/20) | 3.24 s Done.
Done.
-[Task 20/25] Current/Best: 9.73/ 15.07 GFLOPS | Progress: (8/20) | 6.55 s
-[Task 20/25] Current/Best: 2.32/ 16.56 GFLOPS | Progress: (12/20) | 10.42 s
-[Task 20/25] Current/Best: 12.52/ 16.56 GFLOPS | Progress: (16/20) | 14.00 s
-[Task 20/25] Current/Best: 12.77/ 21.83 GFLOPS | Progress: (20/20) | 16.13 s
+[Task 20/25] Current/Best: 9.92/ 15.38 GFLOPS | Progress: (8/20) | 6.64 s
+[Task 20/25] Current/Best: 2.32/ 16.53 GFLOPS | Progress: (12/20) | 10.57 s
+[Task 20/25] Current/Best: 11.10/ 16.53 GFLOPS | Progress: (16/20) | 14.11 s
+[Task 20/25] Current/Best: 12.85/ 22.26 GFLOPS | Progress: (20/20) | 16.20 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.39/ 17.63 GFLOPS | Progress: (4/20) | 3.17 s
-[Task 21/25] Current/Best: 14.58/ 17.63 GFLOPS | Progress: (8/20) | 4.74 s
-[Task 21/25] Current/Best: 1.61/ 17.63 GFLOPS | Progress: (12/20) | 6.85 s
-[Task 21/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (16/20) | 10.28 s
-[Task 21/25] Current/Best: 4.47/ 18.23 GFLOPS | Progress: (20/20) | 17.33 s
+[Task 21/25] Current/Best: 6.42/ 17.76 GFLOPS | Progress: (4/20) | 3.14 s
+[Task 21/25] Current/Best: 14.66/ 17.76 GFLOPS | Progress: (8/20) | 4.70 s
+[Task 21/25] Current/Best: 1.61/ 17.76 GFLOPS | Progress: (12/20) | 6.80 s
+[Task 21/25] Current/Best: 18.17/ 18.17 GFLOPS | Progress: (16/20) | 10.19 s
+[Task 21/25] Current/Best: 4.47/ 18.17 GFLOPS | Progress: (20/20) | 17.22 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 17.02 GFLOPS | Progress: (4/20) | 2.61 s
-[Task 22/25] Current/Best: 8.71/ 21.92 GFLOPS | Progress: (8/20) | 4.59 s
-[Task 22/25] Current/Best: 19.99/ 21.92 GFLOPS | Progress: (12/20) | 6.87 s
-[Task 22/25] Current/Best: 14.95/ 21.92 GFLOPS | Progress: (16/20) | 8.91 s
-[Task 22/25] Current/Best: 14.19/ 21.92 GFLOPS | Progress: (20/20) | 10.62 s Done.
+[Task 22/25] Current/Best: 2.70/ 17.08 GFLOPS | Progress: (4/20) | 2.61 s
+[Task 22/25] Current/Best: 8.75/ 22.07 GFLOPS | Progress: (8/20) | 4.49 s
+[Task 22/25] Current/Best: 20.08/ 22.07 GFLOPS | Progress: (12/20) | 6.76 s
+[Task 22/25] Current/Best: 14.99/ 22.07 GFLOPS | Progress: (16/20) | 8.82 s
+[Task 22/25] Current/Best: 14.15/ 22.07 GFLOPS | Progress: (20/20) | 10.52 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.49/ 20.69 GFLOPS | Progress: (4/20) | 3.16 s
-[Task 23/25] Current/Best: 15.20/ 20.69 GFLOPS | Progress: (8/20) | 6.52 s
-[Task 23/25] Current/Best: 20.95/ 21.66 GFLOPS | Progress: (12/20) | 8.33 s
-[Task 23/25] Current/Best: 6.43/ 21.66 GFLOPS | Progress: (16/20) | 15.21 s
-[Task 23/25] Current/Best: 7.73/ 21.66 GFLOPS | Progress: (20/20) | 19.44 s Done.
+[Task 23/25] Current/Best: 17.69/ 20.80 GFLOPS | Progress: (4/20) | 3.15 s
+[Task 23/25] Current/Best: 14.43/ 20.80 GFLOPS | Progress: (8/20) | 6.48 s
+[Task 23/25] Current/Best: 20.98/ 21.85 GFLOPS | Progress: (12/20) | 8.25 s
+[Task 23/25] Current/Best: 6.51/ 21.85 GFLOPS | Progress: (16/20) | 15.23 s
+[Task 23/25] Current/Best: 8.04/ 21.85 GFLOPS | Progress: (20/20) | 19.41 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.17/ 8.17 GFLOPS | Progress: (4/20) | 11.74 s
-[Task 24/25] Current/Best: 2.15/ 8.17 GFLOPS | Progress: (8/20) | 22.71 s
-[Task 24/25] Current/Best: 4.51/ 8.17 GFLOPS | Progress: (12/20) | 34.18 s Done.
+[Task 24/25] Current/Best: 8.04/ 8.04 GFLOPS | Progress: (4/20) | 11.69 s
+[Task 24/25] Current/Best: 3.62/ 8.04 GFLOPS | Progress: (8/20) | 22.94 s
+[Task 24/25] Current/Best: 4.42/ 8.04 GFLOPS | Progress: (12/20) | 33.64 s Done.
Done.
-[Task 24/25] Current/Best: 6.37/ 8.82 GFLOPS | Progress: (16/20) | 39.60 s
-[Task 24/25] Current/Best: 3.31/ 8.85 GFLOPS | Progress: (20/20) | 45.50 s Done.
+[Task 24/25] Current/Best: 5.86/ 8.83 GFLOPS | Progress: (16/20) | 39.01 s
+[Task 24/25] Current/Best: 3.37/ 9.20 GFLOPS | Progress: (20/20) | 44.88 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/ 2.94 GFLOPS | Progress: (4/20) | 11.53 s
-[Task 25/25] Current/Best: 5.90/ 8.00 GFLOPS | Progress: (8/20) | 22.75 s
-[Task 25/25] Current/Best: 5.90/ 8.00 GFLOPS | Progress: (12/20) | 34.02 s
-[Task 25/25] Current/Best: 5.77/ 9.26 GFLOPS | Progress: (16/20) | 35.72 s
-[Task 25/25] Current/Best: 2.85/ 9.26 GFLOPS | Progress: (20/20) | 46.39 s
+[Task 25/25] Current/Best: 1.55/ 2.82 GFLOPS | Progress: (4/20) | 11.52 s
+[Task 25/25] Current/Best: 6.27/ 8.24 GFLOPS | Progress: (8/20) | 22.72 s
+[Task 25/25] Current/Best: 6.15/ 8.24 GFLOPS | Progress: (12/20) | 33.98 s
+[Task 25/25] Current/Best: 5.96/ 8.78 GFLOPS | Progress: (16/20) | 35.77 s
+[Task 25/25] Current/Best: 2.87/ 9.63 GFLOPS | Progress: (20/20) | 46.42 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -953,8 +953,8 @@ 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': 412.12751948999994, 'median': 412.04843069999697, 'std': 0.6459348994910754}
-unoptimized: {'mean': 492.91474093000033, 'median': 491.8427488500015, 'std': 2.815318947956547}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 407.95035273001304, 'median': 407.77613870000096, 'std': 0.9025302456285362}
+unoptimized: {'mean': 493.1380477699986, 'median': 492.5971845999811, 'std': 1.245634467347975}
</pre></div>
</div>
</div>
@@ -968,7 +968,7 @@ 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 10.323 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 11.814 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 8dbb567df..d47ce4292 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -499,7 +499,7 @@ 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>1.245e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.339e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 86a23a43b..aef502278 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -459,7 +459,7 @@ 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, 0x2164a6d0)), stage(b, placeholder(b, 0x216949b0)), 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, 0xc710720)), stage(b, placeholder(b, 0xbbd1d90)), 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=[it [...]
</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 2dc792344..79ce3b96d 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -303,7 +303,7 @@
<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>12:54.300</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>12:49.553</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,42 +312,42 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:10.323</p></td>
+<td><p>10:11.814</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>00:58.759</p></td>
+<td><p>01:00.723</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>00:51.420</p></td>
+<td><p>00:43.460</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>00:27.828</p></td>
+<td><p>00:27.696</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>00:23.881</p></td>
+<td><p>00:24.226</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>00:01.279</p></td>
+<td><p>00:00.809</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>00:00.667</p></td>
+<td><p>00:00.670</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>00:00.143</p></td>
+<td><p>00:00.156</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index d8bb1278d..09a5a9480 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -566,7 +566,7 @@ 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:264: 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>
@@ -640,10 +640,10 @@ 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 8.051810000324622e-06 1.0
- naive 5.852099999999999e-06 0.7268055256847916
-parallel 6.0782000000000005e-06 0.7548861684211311
- vector 2.45766e-05 3.0523074934715493
+ numpy 8.158410000760341e-06 1.0
+ naive 5.846500000000001e-06 0.7166224790682404
+parallel 6.9463e-06 0.8514281581034324
+ vector 2.4548100000000003e-05 3.0089318871829422
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -959,7 +959,7 @@ 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: 0.018632
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017844
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1002,7 +1002,7 @@ 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:264: 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: 3.235045
+none: 3.409536
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1069,7 +1069,7 @@ 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:264: 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: 0.296574
+blocking: 0.297843
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1130,7 +1130,7 @@ 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:264: 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: 0.334723
+vectorization: 0.332657
@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], []),
@@ -1187,7 +1187,7 @@ 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:264: 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: 0.116859
+loop permutation: 0.120565
@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], []),
@@ -1265,7 +1265,7 @@ 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:264: 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: 0.111147
+array packing: 0.111045
@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], []),
@@ -1341,7 +1341,7 @@ 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:264: 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: 0.110734
+block caching: 0.111168
@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], []),
@@ -1410,7 +1410,7 @@ 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:264: 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: 0.144874
+parallelization: 0.145184
@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], []),
@@ -1472,13 +1472,13 @@ 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 3.2350452699 1.0
- blocking 0.29657368110000004 0.09167528005231518
- vectorization 0.3347226748 0.10346769422807699
-loop permutation 0.11685929129999999 0.03612292303520447
- array packing 0.11114693410000001 0.034357149537952436
- block caching 0.11073384319999999 0.03422945707446713
- parallelization 0.1448742241 0.04478275016673206
+ none 3.4095355486 1.0
+ blocking 0.2978434897 0.08735603000892554
+ vectorization 0.33265705840000004 0.09756667841066897
+loop permutation 0.12056504679999999 0.03536113499374001
+ array packing 0.1110453093 0.03256904282625728
+ block caching 0.11116820680000002 0.03260508805829789
+ parallelization 0.1451835296 0.042581614865289864
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1510,6 +1510,7 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.723 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>